A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Predictive analytics support for complex chronic medical conditions: An experience-based co-design study of physician managers' needs and preferences

PURPOSE

The literature suggests predictive technology applications in health care would benefit from physician and manager input during design and development. The aim was to explore the needs and preferences of physician managers regarding the role of predictive analytics in decision support for patients with the highly complex yet common combination of multiple chronic conditions of cardiovascular (Heart) and kidney (Nephrology) diseases and diabetes (HND).

METHODS

This qualitative study employed an experience-based co-design model comprised of three data gathering phases: 1. Patient mapping through non-participant observations informed by process mining of electronic health records data, 2. Semi-structured experience-based interviews, and 3. A co-design workshop. Data collection was conducted with physician managers working at or collaborating with the HND center, Danderyd University Hospital (DSAB), in Stockholm, Sweden. HND center is an integrated practice unit offering comprehensive person-centered multidisciplinary care to stabilize disease progression, reduce visits, and develop treatment strategies that enables a transition to primary care.

RESULTS

Interview and workshop data described a complex challenge due to the interaction of underlying pathophysiologies and the subsequent need for multiple care givers that hindered care continuity. The HND center partly met this challenge by coordinating care through multiple interprofessional and interdisciplinary shared decision-making interfaces. The large patient datasets were difficult to operationalize in daily practice due to data entry and retrieval issues. Predictive analytics was seen as a potentially effective approach to support decision-making, calculate risks, and improve resource utilization, especially in the context of complex chronic care, and the HND center a good place for pilot testing and development. Simplicity of visual interfaces, a better understanding of the algorithms by the health care professionals, and the need to address professional concerns, were identified as key factors to increase adoption and facilitate implementation.

CONCLUSIONS

The HND center serves as a comprehensive integrated practice unit that integrates different medical disciplinary perspectives in a person-centered care process to address the needs of patients with multiple complex comorbidities. Therefore, piloting predictive technologies at the same time with a high potential for improving care represents an extreme, demanding, and complex case. The study findings show that health care professionals' involvement in the design of predictive technologies right from the outset can facilitate the implementation and adoption of such technologies, as well as enhance their predictive effectiveness and performance. Simplicity in the design of predictive technologies and better understanding of the concept and interpretation of the algorithms may result in implementation of predictive technologies in health care. Institutional efforts are needed to enhance collaboration among the health care professionals and IT professionals for effective development, implementation, and adoption of predictive analytics in health care.

Collating the voice of people with autoimmune diseases: Methodology for the Third Phase of the COVAD Studies

INTRODUCTION

The growing recognition of holistic patient care highlights the various factors shaping the quality of life of individuals with autoimmune and rheumatic diseases (AIRDs). Beyond the traditional disease measures, there is an emerging acknowledgment of the less-explored aspects, including subjective well-being, social determinants of health, comorbidities, mental health, and medication adherence. Moreover, digital health services have empowered patients to engage actively in decision-making alongside clinicians. To explore these domains within the context of AIRDs, the "Collating the Voice of People with Autoimmune Diseases" COVAD survey was conceived, a successor of the previous two COVAD surveys. In this document, we present the study protocol in comprehensive detail.

METHODS

The COVAD-3 survey is a cross-sectional patient self-reported e-survey incorporating multiple widely accepted scales/scores to assess various aspects of patients' lifestyles objectively. To ensure the survey's accuracy and usability across diverse regions, it will be translated into multiple languages and subjected to rigorous vetting and pilot testing. It will be distributed by collaborators via online platforms and data will be collected from patients with AIRDs, and healthy individuals over eight months. Data analysis will focus on outcome measures related to various social, demographic, economic, and psychological factors.

CONCLUSION

With the increasing awareness to adopt a holistic treatment approach encompassing all avenues of life, the COVAD-3 survey aims to gain valuable insights into the impact of social, demographic, economic, and psychological determinants of health on the subjective well-being in patients with AIRDs, which will contribute to a better understanding of their overall health and well-being.

Machine learning techniques for prediction in pregnancy complicated by autoimmune rheumatic diseases: Applications and challenges

Autoimmune rheumatic diseases are chronic conditions affecting multiple systems and often occurring in young women of childbearing age. The diseases and the physiological characteristics of pregnancy significantly impact maternal-fetal health and pregnancy outcomes. Currently, the integration of big data with healthcare has led to the increasing popularity of using machine learning (ML) to mine clinical data for studying pregnancy complications. In this review, we introduce the basics of ML and the recent advances and trends of ML in different prediction applications for common pregnancy complications by autoimmune rheumatic diseases. Finally, the challenges and future for enhancing the accuracy, reliability, and clinical applicability of ML in prediction have been discussed. This review will provide insights into the utilization of ML in identifying and assisting clinical decision-making for pregnancy complications, while also establishing a foundation for exploring comprehensive management strategies for pregnancy and enhancing maternal and child health.

Predictive model for assessing malnutrition in elderly hospitalized cancer patients: A machine learning approach

BACKGROUND

Malnutrition is prevalent among elderly cancer patients. This study aims to develop a predictive model for malnutrition in hospitalized elderly cancer patients.

METHODS

Data from January 2022 to January 2023 on cancer patients aged 60+ were collected, involving 22 variables. Key variables were identified using the LASSO (Least Absolute Shrinkage and Selection Operator) method, and nine machine learning models were tested. SHAP was used to interpret the XGBoost model. Malnutrition prevalence was assessed.

RESULTS

Among 450 participants, 46.4 % were malnourished. Key predictors identified were ADL (Activities of Daily Living), ALB (Albumin), BMI (Body Mass Index) and age. XGBoost had the highest AUC of 0.945, accuracy of 0.872, and sensitivity of 0.968. Higher ADL and age increased malnutrition risk, while lower ALB and BMI reduced it.

CONCLUSIONS

The XGBoost model is highly effective in detecting malnutrition in elderly cancer patients, enabling early and rapid nutritional assessments.

Modeling and simulation for prediction of multiple sclerosis progression

In light of extensive work that has created a wide range of techniques for predicting the course of multiple sclerosis (MS) disease, this paper attempts to provide an overview of these approaches and put forth an alternative way to predict the disease progression. For this purpose, the existing methods for estimating and predicting the course of the disease have been categorized into clinical, radiological, biological, and computational or artificial intelligence-based markers. Weighing the weaknesses and strengths of these prognostic groups is a profound method that is yet in need and works directly at the level of diseased connectivity. Therefore, we propose using the computational models in combination with established connectomes as a predictive tool for MS disease trajectories. The fundamental conduction-based Hodgkin-Huxley model emerged as promising from examining these studies. The advantage of the Hodgkin-Huxley model is that certain properties of connectomes, such as neuronal connection weights, spatial distances, and adjustments of signal transmission rates, can be taken into account. It is precisely these properties that are particularly altered in MS and that have strong implications for processing, transmission, and interactions of neuronal signaling patterns. The Hodgkin-Huxley (HH) equations as a point-neuron model are used for signal propagation inside a small network. The objective is to change the conduction parameter of the neuron model, replicate the changes in myelin properties in MS and observe the dynamics of the signal propagation across the network. The model is initially validated for different lengths, conduction values, and connection weights through three nodal connections. Later, these individual factors are incorporated into a small network and simulated to mimic the condition of MS. The signal propagation pattern is observed after inducing changes in conduction parameters at certain nodes in the network and compared against a control model pattern obtained before the changes are applied to the network. The signal propagation pattern varies as expected by adapting to the input conditions. Similarly, when the model is applied to a connectome, the pattern changes could give an insight into disease progression. This approach has opened up a new path to explore the progression of the disease in MS. The work is in its preliminary state, but with a future vision to apply this method in a connectome, providing a better clinical tool.

Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning

OBJECTIVE

The macrophage activation syndrome (MAS) secondary to systemic lupus erythematosus (SLE) is a severe and life-threatening complication. Early diagnosis of MAS is particularly challenging. In this study, machine learning models and diagnostic scoring card were developed to aid in clinical decision-making using clinical characteristics.

METHODS

We retrospectively collected clinical data from 188 patients with either SLE or the MAS secondary to SLE. 13 significant clinical predictor variables were filtered out using the Least Absolute Shrinkage and Selection Operator (LASSO). These variables were subsequently utilized as inputs in five machine learning models. The performance of the models was evaluated using the area under the receiver operating characteristic curve (ROC-AUC), F1 score, and F2 score. To enhance clinical usability, we developed a diagnostic scoring card based on logistic regression (LR) analysis and Chi-Square binning, establishing probability thresholds and stratification for the card. Additionally, this study collected data from four other domestic hospitals for external validation.

RESULTS

Among all the machine learning models, the LR model demonstrates the highest level of performance in internal validation, achieving a ROC-AUC of 0.998, an F1 score of 0.96, and an F2 score of 0.952. The score card we constructed identifies the probability threshold at a score of 49, achieving a ROC-AUC of 0.994 and an F2 score of 0.936. The score results were categorized into five groups based on diagnostic probability: extremely low (below 5%), low (5-25%), normal (25-75%), high (75-95%), and extremely high (above 95%). During external validation, the performance evaluation revealed that the Support Vector Machine (SVM) model outperformed other models with an AUC value of 0.947, and the scorecard model has an AUC of 0.915. Additionally, we have established an online assessment system for early identification of MAS secondary to SLE.

CONCLUSION

Machine learning models can significantly improve the diagnostic accuracy of MAS secondary to SLE, and the diagnostic scorecard model can facilitate personalized probabilistic predictions of disease occurrence in clinical environments.

Machine learning diagnosis of active Juvenile Idiopathic Arthritis on blood pool [ 99M Tc] Tc-MDP scintigraphy images

PURPOSE

Neural network has widely been applied for medical classifications and disease diagnosis. This study employs deep learning to best discriminate Juvenile Idiopathic Arthritis (JIA), a pediatric chronic joint inflammatory disease, from healthy joints by exploring blood pool images of 2phase [ 99m Tc] Tc-MDP bone scintigraphy.

METHODS

Self-deigned multi-input Convolutional Neural Network (CNN) in addition to three available pre-trained models including VGG16, ResNet50 and Xception are applied on 1304 blood pool images of 326 healthy and known JIA children and adolescents (aged 1-16).

RESULTS

The self-designed model ROC analysis shows diagnostic efficiency with Area Under the Curve (AUC) 0.82 and 0.86 for knee and ankle joints, respectively. Among the three pertained models, VGG16 ROC analysis reveals AUC 0.76 and 0.81 for knee and ankle images, respectively.

CONCLUSION

The self-designed model shows best performance on blood pool scintigraph diagnosis of patients with JIA. VGG16 was the most efficient model rather to other pre-trained networks. This study can pave the way of artificial intelligence (AI) application in nuclear medicine for the diagnosis of pediatric inflammatory disease.

Deep learning-augmented T-junction droplet generation

Droplet generation technology has become increasingly important in a wide range of applications, including biotechnology and chemical synthesis. T-junction channels are commonly used for droplet generation due to their integration capability of a larger number of droplet generators in a compact space. In this study, a finite element analysis (FEA) approach is employed to simulate droplet production and its dynamic regimes in a T-junction configuration and collect data for post-processing analysis. Next, image analysis was performed to calculate the droplet length and determine the droplet generation regime. Furthermore, machine learning (ML) and deep learning (DL) algorithms were applied to estimate outputs through examination of input parameters within the simulation range. At the end, a graphical user interface (GUI) was developed for estimation of the droplet characteristics based on inputs, enabling the users to preselect their designs with comparable microfluidic configurations within the studied range.

The relationship between heavy metals and metabolic syndrome using machine learning

Background

Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.

Methods

The data used in this study are from the national health and nutrition examination survey 2003-2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.

Results

11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.

Conclusion

Our study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model.

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.

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

Genome-wide association studies (GWAS) have identified thousands of variants in the human genome with autoimmune diseases. However, identifying functional regulatory variants associated with autoimmune diseases remains challenging, largely because of insufficient experimental validation data. We adopt the concept of semi-supervised learning by combining labeled and unlabeled data to develop a deep learning-based algorithm framework, sscNOVA, to predict functional regulatory variants in autoimmune diseases and analyze the functional characteristics of these regulatory variants. Compared to traditional supervised learning methods, our approach leverages more variants' data to explore the relationship between functional regulatory variants and autoimmune diseases. Based on the experimentally curated testing dataset and evaluation metrics, we find that sscNOVA outperforms other state-of-the-art methods. Furthermore, we illustrate that sscNOVA can help to improve the prioritization of functional regulatory variants from lead single-nucleotide polymorphisms and the proxy variants in autoimmune GWAS data.

Biomimetic Wearable Sensors: Emerging Combination of Intelligence and Electronics

Owing to the advancement of interdisciplinary concepts, for example, wearable electronics, bioelectronics, and intelligent sensing, during the microelectronics industrial revolution, nowadays, extensively mature wearable sensing devices have become new favorites in the noninvasive human healthcare industry. The combination of wearable sensing devices with bionics is driving frontier developments in various fields, such as personalized medical monitoring and flexible electronics, due to the superior biocompatibilities and diverse sensing mechanisms. It is noticed that the integration of desired functions into wearable device materials can be realized by grafting biomimetic intelligence. Therefore, herein, the mechanism by which biomimetic materials satisfy and further enhance system functionality is reviewed. Next, wearable artificial sensory systems that integrate biomimetic sensing into portable sensing devices are introduced, which have received significant attention from the industry owing to their novel sensing approaches and portabilities. To address the limitations encountered by important signal and data units in biomimetic wearable sensing systems, two paths forward are identified and current challenges and opportunities are presented in this field. In summary, this review provides a further comprehensive understanding of the development of biomimetic wearable sensing devices from both breadth and depth perspectives, offering valuable guidance for future research and application expansion of these devices.

Exploratory clinical subgroup clustering in systemic sclerosis: Results from the Indian Progressive Systemic Sclerosis Registry

Objective

To conduct an exploratory cluster analysis of systemic sclerosis patients from the baseline data of the Indian systemic sclerosis registry.

Methods

Patients satisfying American College of Rheumatology-European League Against Rheumatism classification criteria for systemic sclerosis were included. The clusters formed using clinical and immunological parameters were compared.

Results

Of the 564 systemic sclerosis registry participants, 404 patients were included. We derived four clusters of which three were anti-topoisomerase I predominant and one was anti-centromere antibody 2 dominant. Cluster 1 (n-82 (20.3%)) had diffuse cutaneous systemic sclerosis patients with the most severe skin disease, anti-topoisomerase I positivity, males, younger age of onset and high prevalence of musculoskeletal, vasculopathic and gastrointestinal features. Cluster 2 (n-141 (34.9%)) was also diffuse cutaneous systemic sclerosis and anti-topoisomerase I predominant but with less severe skin phenotype than cluster 1 and a lesser prevalence of musculoskeletal, vasculopathic and gastrointestinal features. Cluster 3 (n-119 (29.5%)) had limited cutaneous systemic sclerosis patients with anti-topoisomerase I positivity along with other antibodies. The proximal muscle weakness was higher and digital pitting scars were lower, while other organ involvement was similar between clusters 2 and 3. Cluster 4 (n-62 (15.30%)) was the least severe group with limited cutaneous systemic sclerosis and anti-centromere antibody predominance. Age of onset was higher with low musculoskeletal disease and a higher presence of upper gastrointestinal features. The prevalence of interstitial lung disease was similar in the three anti-topoisomerase I predominant clusters.

Conclusion

With exploratory cluster analysis, we confirmed the possibility of subclassification of systemic sclerosis along a spectrum based on clinical and immunological characteristics. We also corroborated the presence of anti-topoisomerase I in limited cutaneous systemic sclerosis and the association of interstitial lung disease with anti-topoisomerase I.

Can adverse childhood experiences predict chronic health conditions? Development of trauma-informed, explainable machine learning models

Introduction

Decades of research have established the association between adverse childhood experiences (ACEs) and adult onset of chronic diseases, influenced by health behaviors and social determinants of health (SDoH). Machine Learning (ML) is a powerful tool for computing these complex associations and accurately predicting chronic health conditions.

Methods

Using the 2021 Behavioral Risk Factor Surveillance Survey, we developed several ML models-random forest, logistic regression, support vector machine, Naïve Bayes, and K-Nearest Neighbor-over data from a sample of 52,268 respondents. We predicted 13 chronic health conditions based on ACE history, health behaviors, SDoH, and demographics. We further assessed each variable's importance in outcome prediction for model interpretability. We evaluated model performance via the Area Under the Curve (AUC) score.

Results

With the inclusion of data on ACEs, our models outperformed or demonstrated similar accuracies to existing models in the literature that used SDoH to predict health outcomes. The most accurate models predicted diabetes, pulmonary diseases, and heart attacks. The random forest model was the most effective for diabetes (AUC = 0.784) and heart attacks (AUC = 0.732), and the logistic regression model most accurately predicted pulmonary diseases (AUC = 0.753). The strongest predictors across models were age, ever monitored blood sugar or blood pressure, count of the monitoring behaviors for blood sugar or blood pressure, BMI, time of last cholesterol check, employment status, income, count of vaccines received, health insurance status, and total ACEs. A cumulative measure of ACEs was a stronger predictor than individual ACEs.

Discussion

Our models can provide an interpretable, trauma-informed framework to identify and intervene with at-risk individuals early to prevent chronic health conditions and address their inequalities in the U.S.

Machine learning approaches to identify systemic lupus erythematosus in anti-nuclear antibody-positive patients using genomic data and electronic health records

BACKGROUND

Although the 2019 EULAR/ACR classification criteria for systemic lupus erythematosus (SLE) has required at least a positive anti-nuclear antibody (ANA) titer (≥ 1:80), it remains challenging for clinicians to identify patients with SLE. This study aimed to develop a machine learning (ML) approach to assist in the detection of SLE patients using genomic data and electronic health records.

METHODS

Participants with a positive ANA (≥ 1:80) were enrolled from the Taiwan Precision Medicine Initiative cohort. The Taiwan Biobank version 2 array was used to detect single nucleotide polymorphism (SNP) data. Six ML models, Logistic Regression, Random Forest (RF), Support Vector Machine, Light Gradient Boosting Machine, Gradient Tree Boosting, and Extreme Gradient Boosting (XGB), were used to identify SLE patients. The importance of the clinical and genetic features was determined by Shapley Additive Explanation (SHAP) values. A logistic regression model was applied to identify genetic variations associated with SLE in the subset of patients with an ANA equal to or exceeding 1:640.

RESULTS

A total of 946 SLE and 1,892 non-SLE controls were included in this analysis. Among the six ML models, RF and XGB demonstrated superior performance in the differentiation of SLE from non-SLE. The leading features in the SHAP diagram were anti-double strand DNA antibodies, ANA titers, AC4 ANA pattern, polygenic risk scores, complement levels, and SNPs. Additionally, in the subgroup with a high ANA titer (≥ 1:640), six SNPs positively associated with SLE and five SNPs negatively correlated with SLE were discovered.

CONCLUSIONS

ML approaches offer the potential to assist in diagnosing SLE and uncovering novel SNPs in a group of patients with autoimmunity.

Decoding the mitochondrial connection: development and validation of biomarkers for classifying and treating systemic lupus erythematosus through bioinformatics and machine learning

BACKGROUND

Systemic lupus erythematosus (SLE) is a multifaceted autoimmune disease characterized by clinical and pathological diversity. Mitochondrial dysfunction has been identified as a critical pathogenetic factor in SLE. However, the specific molecular aspects and regulatory roles of this dysfunction in SLE are not fully understood. Our study aims to explore the molecular characteristics of mitochondria-related genes (MRGs) in SLE, with a focus on identifying reliable biomarkers for classification and therapeutic purposes.

METHODS

We sourced six SLE-related microarray datasets (GSE61635, GSE50772, GSE30153, GSE99967, GSE81622, and GSE49454) from the Gene Expression Omnibus (GEO) database. Three of these datasets (GSE61635, GSE50772, GSE30153) were integrated into a training set for differential analysis. The intersection of differentially expressed genes with MRGs yielded a set of differentially expressed MRGs (DE-MRGs). We employed machine learning algorithms-random forest (RF), support vector machine (SVM), and least absolute shrinkage and selection operator (LASSO) logistic regression-to select key hub genes. These genes' classifying potential was validated in the training set and three other validation sets (GSE99967, GSE81622, and GSE49454). Further analyses included differential expression, co-expression, protein-protein interaction (PPI), gene set enrichment analysis (GSEA), and immune infiltration, centered on these hub genes. We also constructed TF-mRNA, miRNA-mRNA, and drug-target networks based on these hub genes using the ChEA3, miRcode, and PubChem databases.

RESULTS

Our investigation identified 761 differentially expressed genes (DEGs), mainly related to viral infection, inflammatory, and immune-related signaling pathways. The interaction between these DEGs and MRGs led to the identification of 27 distinct DE-MRGs. Key among these were FAM210B, MSRB2, LYRM7, IFI27, and SCO2, designated as hub genes through machine learning analysis. Their significant role in SLE classification was confirmed in both the training and validation sets. Additional analyses included differential expression, co-expression, PPI, GSEA, immune infiltration, and the construction of TF-mRNA, miRNA-mRNA, and drug-target networks.

CONCLUSIONS

This research represents a novel exploration into the MRGs of SLE, identifying FAM210B, MSRB2, LYRM7, IFI27, and SCO2 as significant candidates for classifying and therapeutic targeting.

Performances of machine learning algorithms in discriminating sacroiliitis features on MRI: a systematic review

OBJECTIVES

Summarise the evidence of the performance of the machine learning algorithm in discriminating sacroiliitis features on MRI and compare it with the accuracy of human physicians.

METHODS

MEDLINE, EMBASE, CIHNAL, Web of Science, IEEE, American College of Rheumatology and European Alliance of Associations for Rheumatology abstract archives were searched for studies published between 2008 and 4 June 2023. Two authors independently screened and extracted the variables, and the results are presented using tables and forest plots.

RESULTS

Ten studies were selected from 2381. Over half of the studies used deep learning models, using Assessment of Spondyloarthritis International Society sacroiliitis criteria as the ground truth, and manually extracted the regions of interest. All studies reported the area under the curve as a performance index, ranging from 0.76 to 0.99. Sensitivity and specificity were the second-most commonly reported indices, with sensitivity ranging from 0.56 to 1.00 and specificity ranging from 0.67 to 1.00; these results are comparable to a radiologist's sensitivity of 0.67-1.00 and specificity of 0.78-1.00 in the same cohort. More than half of the studies showed a high risk of bias in the analysis domain of quality appraisal owing to the small sample size or overfitting issues.

CONCLUSION

The performance of machine learning algorithms in discriminating sacroiliitis features on MRI varied owing to the high heterogeneity between studies and the small sample sizes, overfitting, and under-reporting issues of individual studies. Further well-designed and transparent studies are required.

Supervised Machine Learning Classifies Inflammatory Bowel Disease Patients by Subtype Using Whole Exome Sequencing Data

BACKGROUND

Inflammatory bowel disease [IBD] is a chronic inflammatory disorder with two main subtypes: Crohn's disease [CD] and ulcerative colitis [UC]. Prompt subtype diagnosis enables the correct treatment to be administered. Using genomic data, we aimed to assess machine learning [ML] to classify patients according to IBD subtype.

METHODS

Whole exome sequencing [WES] from paediatric/adult IBD patients was processed using an in-house bioinformatics pipeline. These data were condensed into the per-gene, per-individual genomic burden score, GenePy. Data were split into training and testing datasets [80/20]. Feature selection with a linear support vector classifier, and hyperparameter tuning with Bayesian Optimisation, were performed [training data]. The supervised ML method random forest was utilised to classify patients as CD or UC, using three panels: 1] all available genes; 2] autoimmune genes; 3] 'IBD' genes. ML results were assessed using area under the receiver operating characteristics curve [AUROC], sensitivity, and specificity on the testing dataset.

RESULTS

A total of 906 patients were included in analysis [600 CD, 306 UC]. Training data included 488 patients, balanced according to the minority class of UC. The autoimmune gene panel generated the best performing ML model [AUROC = 0.68], outperforming an IBD gene panel [AUROC = 0.61]. NOD2 was the top gene for discriminating CD and UC, regardless of the gene panel used. Lack of variation in genes with high GenePy scores in CD patients was the best classifier of a diagnosis of UC.

DISCUSSION

We demonstrate promising classification of patients by subtype using random forest and WES data. Focusing on specific subgroups of patients, with larger datasets, may result in better classification.

Physicians' and Machine Learning Researchers' Perspectives on Ethical Issues in the Early Development of Clinical Machine Learning Tools: Qualitative Interview Study

BACKGROUND

Innovative tools leveraging artificial intelligence (AI) and machine learning (ML) are rapidly being developed for medicine, with new applications emerging in prediction, diagnosis, and treatment across a range of illnesses, patient populations, and clinical procedures. One barrier for successful innovation is the scarcity of research in the current literature seeking and analyzing the views of AI or ML researchers and physicians to support ethical guidance.

OBJECTIVE

This study aims to describe, using a qualitative approach, the landscape of ethical issues that AI or ML researchers and physicians with professional exposure to AI or ML tools observe or anticipate in the development and use of AI and ML in medicine.

METHODS

Semistructured interviews were used to facilitate in-depth, open-ended discussion, and a purposeful sampling technique was used to identify and recruit participants. We conducted 21 semistructured interviews with a purposeful sample of AI and ML researchers (n=10) and physicians (n=11). We asked interviewees about their views regarding ethical considerations related to the adoption of AI and ML in medicine. Interviews were transcribed and deidentified by members of our research team. Data analysis was guided by the principles of qualitative content analysis. This approach, in which transcribed data is broken down into descriptive units that are named and sorted based on their content, allows for the inductive emergence of codes directly from the data set.

RESULTS

Notably, both researchers and physicians articulated concerns regarding how AI and ML innovations are shaped in their early development (ie, the problem formulation stage). Considerations encompassed the assessment of research priorities and motivations, clarity and centeredness of clinical needs, professional and demographic diversity of research teams, and interdisciplinary knowledge generation and collaboration. Phase-1 ethical issues identified by interviewees were notably interdisciplinary in nature and invited questions regarding how to align priorities and values across disciplines and ensure clinical value throughout the development and implementation of medical AI and ML. Relatedly, interviewees suggested interdisciplinary solutions to these issues, for example, more resources to support knowledge generation and collaboration between developers and physicians, engagement with a broader range of stakeholders, and efforts to increase diversity in research broadly and within individual teams.

CONCLUSIONS

These qualitative findings help elucidate several ethical challenges anticipated or encountered in AI and ML for health care. Our study is unique in that its use of open-ended questions allowed interviewees to explore their sentiments and perspectives without overreliance on implicit assumptions about what AI and ML currently are or are not. This analysis, however, does not include the perspectives of other relevant stakeholder groups, such as patients, ethicists, industry researchers or representatives, or other health care professionals beyond physicians. Additional qualitative and quantitative research is needed to reproduce and build on these findings.

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.

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods of plant phenotyping, while valuable, are limited in their ability to capture the complexity of plant biology. The advent of (meta-)genomics, (meta-)transcriptomics, proteomics, and metabolomics has provided an opportunity for a more comprehensive analysis. AI and machine learning (ML) techniques can effectively handle the complexity and volume of multi-omics data, providing meaningful interpretations and predictions. Reflecting the multidisciplinary nature of this area of research, in this review, readers will find a collection of state-of-the-art solutions that are key to the integration of multi-omics data and AI for phenotyping experiments in horticulture, including experimental design considerations with several technical and non-technical challenges, which are discussed along with potential solutions. The future prospects of this integration include precision horticulture, predictive breeding, improved disease and stress response management, sustainable crop management, and exploration of plant biodiversity. The integration of multi-omics and AI holds immense promise for revolutionizing horticultural research and applications, heralding a new era in plant phenotyping.

The prognostic value of whole-genome DNA methylation in response to Leflunomide in patients with Rheumatoid Arthritis

Objective

Although Leflunomide (LEF) is effective in treating rheumatoid arthritis (RA), there are still a considerable number of patients who respond poorly to LEF treatment. Till date, few LEF efficacy-predicting biomarkers have been identified. Herein, we explored and developed a DNA methylation-based predictive model for LEF-treated RA patient prognosis.

Methods

Two hundred forty-five RA patients were prospectively enrolled from four participating study centers. A whole-genome DNA methylation profiling was conducted to identify LEF-related response signatures via comparison of 40 samples using Illumina 850k methylation arrays. Furthermore, differentially methylated positions (DMPs) were validated in the 245 RA patients using a targeted bisulfite sequencing assay. Lastly, prognostic models were developed, which included clinical characteristics and DMPs scores, for the prediction of LEF treatment response using machine learning algorithms.

Results

We recognized a seven-DMP signature consisting of cg17330251, cg19814518, cg20124410, cg21109666, cg22572476, cg23403192, and cg24432675, which was effective in predicting RA patient's LEF response status. In the five machine learning algorithms, the support vector machine (SVM) algorithm provided the best predictive model, with the largest discriminative ability, accuracy, and stability. Lastly, the AUC of the complex model(the 7-DMP scores with the lymphocyte and the diagnostic age) was higher than the simple model (the seven-DMP signature, AUC:0.74 vs 0.73 in the test set).

Conclusion

In conclusion, we constructed a prognostic model integrating a 7-DMP scores with the clinical patient profile to predict responses to LEF treatment. Our model will be able to effectively guide clinicians in determining whether a patient is LEF treatment sensitive or not.

A Brief Review of Artificial Intelligence in Genitourinary Oncological Imaging

Genitourinary (GU) system is among the most commonly involved malignancy sites in the human body. Imaging plays a crucial role not only in diagnosis of cancer but also in disease management and its prognosis. However, interpretation of conventional imaging methods such as CT or MR imaging (MRI) usually demonstrates variability across different readers and institutions. Artificial intelligence (AI) has emerged as a promising technology that could improve the patient care by providing helpful input to human readers through lesion detection algorithms and lesion classification systems. Moreover, the robustness of these models may be valuable in automating time-consuming tasks such as organ and lesion segmentations. Herein, we review the current state of imaging and existing challenges in GU malignancies, particularly for cancers of prostate, kidney and bladder; and briefly summarize the recent AI-based solutions to these challenges.

Artificial intelligence-driven drug development against autoimmune diseases

Artificial intelligence (AI)-based predictive models are being used to foster a precision medicine approach to treat complex chronic diseases such as autoimmune and autoinflammatory disorders (AIIDs). In the past few years the first models of systemic lupus erythematosus (SLE), primary Sjögren syndrome (pSS), and rheumatoid arthritis (RA) have been produced by molecular profiling of patients using omic technologies and integrating the data with AI. These advances have confirmed a complex pathophysiology involving multiple proinflammatory pathways and also provide evidence for shared molecular dysregulation across different AIIDs. I discuss how models are used to stratify patients, assess causality in pathophysiology, design drug candidates in silico, and predict drug efficacy in virtual patients. By relating individual patient characteristics to the predicted properties of millions of drug candidates, these models can improve the management of AIIDs through more personalized treatments.

Unveiling the Comorbidities of Chronic Diseases in Serbia Using ML Algorithms and Kohonen Self-Organizing Maps for Personalized Healthcare Frameworks

In previous years, significant attempts have been made to enhance computer-aided diagnosis and prediction applications. This paper presents the results obtained using different machine learning (ML) algorithms and a special type of a neural network map to uncover previously unknown comorbidities associated with chronic diseases, allowing for fast, accurate, and precise predictions. Furthermore, we are presenting a comparative study on different artificial intelligence (AI) tools like the Kohonen self-organizing map (SOM) neural network, random forest, and decision tree for predicting 17 different chronic non-communicable diseases such as asthma, chronic lung diseases, myocardial infarction, coronary heart disease, hypertension, stroke, arthrosis, lower back diseases, cervical spine diseases, diabetes mellitus, allergies, liver cirrhosis, urinary tract diseases, kidney diseases, depression, high cholesterol, and cancer. The research was developed as an observational cross-sectional study through the support of the European Union project, with the data collected from the largest Institute of Public Health "Dr. Milan Jovanovic Batut" in Serbia. The study found that hypertension is the most prevalent disease in Sumadija and western Serbia region, affecting 9.8% of the population, and it is particularly prominent in the age group of 65 to 74 years, with a prevalence rate of 33.2%. The use of Random Forest algorithms can also aid in identifying comorbidities associated with hypertension, with the highest number of comorbidities established as 11. These findings highlight the potential for ML algorithms to provide accurate and personalized diagnoses, identify risk factors and interventions, and ultimately improve patient outcomes while reducing healthcare costs. Moreover, they will be utilized to develop targeted public health interventions and policies for future healthcare frameworks to reduce the burden of chronic diseases in Serbia.

Precision Vaccinology Approaches for the Development of Adjuvanted Vaccines Targeted to Distinct Vulnerable Populations

Infection persists as one of the leading global causes of morbidity and mortality, with particular burden at the extremes of age and in populations who are immunocompromised or suffer chronic co-morbid diseases. By focusing discovery and innovation efforts to better understand the phenotypic and mechanistic differences in the immune systems of diverse vulnerable populations, emerging research in precision vaccine discovery and development has explored how to optimize immunizations across the lifespan. Here, we focus on two key elements of precision vaccinology, as applied to epidemic/pandemic response and preparedness, including (a) selecting robust combinations of adjuvants and antigens, and (b) coupling these platforms with appropriate formulation systems. In this context, several considerations exist, including the intended goals of immunization (e.g., achieving immunogenicity versus lessening transmission), reducing the likelihood of adverse reactogenicity, and optimizing the route of administration. Each of these considerations is accompanied by several key challenges. On-going innovation in precision vaccinology will expand and target the arsenal of vaccine components for protection of vulnerable populations.

A machine learning model identifies patients in need of autoimmune disease testing using electronic health records

Systemic autoimmune rheumatic diseases (SARDs) can lead to irreversible damage if left untreated, yet these patients often endure long diagnostic journeys before being diagnosed and treated. Machine learning may help overcome the challenges of diagnosing SARDs and inform clinical decision-making. Here, we developed and tested a machine learning model to identify patients who should receive rheumatological evaluation for SARDs using longitudinal electronic health records of 161,584 individuals from two institutions. The model demonstrated high performance for predicting cases of autoantibody-tested individuals in a validation set, an external test set, and an independent cohort with a broader case definition. This approach identified more individuals for autoantibody testing compared with current clinical standards and a greater proportion of autoantibody carriers among those tested. Diagnoses of SARDs and other autoimmune conditions increased with higher model probabilities. The model detected a need for autoantibody testing and rheumatology encounters up to five years before the test date and assessment date, respectively. Altogether, these findings illustrate that the clinical manifestations of a diverse array of autoimmune conditions are detectable in electronic health records using machine learning, which may help systematize and accelerate autoimmune testing.

Biomarker-driven development of new therapies for autoimmune diseases: current status and future promises

INTRODUCTION

Auto-immune diseases are complex and heterogeneous. Various types of biomarkers can be used to support precision medicine approaches to autoimmune diseases, ensuring that the right patient receives the most appropriate therapy to improve treatment outcomes.

AREAS COVERED

We review the recent progress made in modeling several autoimmune diseases such as Systemic Lupus Erythematosus, primary Sjogren Syndrome, and Rheumatoid Arthritis following extensive molecular profiling of large cohorts of patients. From this knowledge, BMKs are being identified which support diagnostic as well as patient stratification and prediction of response to treatment. The identification of biomarkers should be initiated early in drug development and properly validated during subsequent clinical trials. To ensure the robustness and reproducibility of biomarkers, the PERMIT Consortium recently established recommendations highlighting the importance of relevant study design, sample size, and appropriate validation of analytical methods.

EXPERT OPINION

The integration by AI-powered analytics of massive data provided by multi-omics technologies, high-resolution medical imaging and sensors borne by patients will eventually allow the identification of clinically relevant BMKs, likely in the form of combinatorial predictive algorithms, to support future drug development for autoimmune diseases.

Artificial intelligence and high-dimensional technologies in the theragnosis of systemic lupus erythematosus

Systemic lupus erythematosus is a complex, systemic autoimmune disease characterised by immune dysregulation. Pathogenesis is multifactorial, contributing to clinical heterogeneity and posing challenges for diagnosis and treatment. Although strides in treatment options have been made in the past 15 years, with the US Food and Drug Administration approval of belimumab in 2011, there are still many patients who have inadequate responses to therapy. A better understanding of underlying disease mechanisms with a holistic and multiparametric approach is required to improve clinical assessment and treatment. This Review discusses the evolution of genomics, epigenomics, transcriptomics, and proteomics in the study of systemic lupus erythematosus and ways to amalgamate these silos of data with a systems-based approach while also discussing ways to strengthen the overall process. These mechanistic insights will facilitate the discovery of functionally relevant biomarkers to guide rational therapeutic selection to improve patient outcomes.

Multimodal-neuroimaging machine-learning analysis of motor disability in multiple sclerosis

Motor disability is a dominant and restricting symptom in multiple sclerosis, yet its neuroimaging correlates are not fully understood. We apply statistical and machine learning techniques on multimodal neuroimaging data to discriminate between multiple sclerosis patients and healthy controls and to predict motor disability scores in the patients. We examine the data of sixty-four multiple sclerosis patients and sixty-five controls, who underwent the MRI examination and the evaluation of motor disability scales. The modalities used comprised regional fractional anisotropy, regional grey matter volumes, and functional connectivity. For analysis, we employ two approaches: high-dimensional support vector machines run on features selected by Fisher Score (aiming for maximal classification accuracy), and low-dimensional logistic regression on the principal components of data (aiming for increased interpretability). We apply analogous regression methods to predict symptom severity. While fractional anisotropy provides the classification accuracy of 96.1% and 89.9% with both approaches respectively, including other modalities did not bring further improvement. Concerning the prediction of motor impairment, the low-dimensional approach performed more reliably. The first grey matter volume component was significantly correlated (R = 0.28-0.46, p < 0.05) with most clinical scales. In summary, we identified the relationship between both white and grey matter changes and motor impairment in multiple sclerosis. Furthermore, we were able to achieve the highest classification accuracy based on quantitative MRI measures of tissue integrity between patients and controls yet reported, while also providing a low-dimensional classification approach with comparable results, paving the way to interpretable machine learning models of brain changes in multiple sclerosis.

Systematic review identifies the design and methodological conduct of studies on machine learning-based prediction models

BACKGROUND AND OBJECTIVES

We sought to summarize the study design, modelling strategies, and performance measures reported in studies on clinical prediction models developed using machine learning techniques.

METHODS

We search PubMed for articles published between 01/01/2018 and 31/12/2019, describing the development or the development with external validation of a multivariable prediction model using any supervised machine learning technique. No restrictions were made based on study design, data source, or predicted patient-related health outcomes.

RESULTS

We included 152 studies, 58 (38.2% [95% CI 30.8-46.1]) were diagnostic and 94 (61.8% [95% CI 53.9-69.2]) prognostic studies. Most studies reported only the development of prediction models (n = 133, 87.5% [95% CI 81.3-91.8]), focused on binary outcomes (n = 131, 86.2% [95% CI 79.8-90.8), and did not report a sample size calculation (n = 125, 82.2% [95% CI 75.4-87.5]). The most common algorithms used were support vector machine (n = 86/522, 16.5% [95% CI 13.5-19.9]) and random forest (n = 73/522, 14% [95% CI 11.3-17.2]). Values for area under the Receiver Operating Characteristic curve ranged from 0.45 to 1.00. Calibration metrics were often missed (n = 494/522, 94.6% [95% CI 92.4-96.3]).

CONCLUSION

Our review revealed that focus is required on handling of missing values, methods for internal validation, and reporting of calibration to improve the methodological conduct of studies on machine learning-based prediction models.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO, CRD42019161764.

Top-Down Proteomics Detection of Potential Salivary Biomarkers for Autoimmune Liver Diseases Classification

(1) Autoimmune hepatitis (AIH) and primary biliary cholangitis (PBC) are autoimmune liver diseases characterized by chronic hepatic inflammation and progressive liver fibrosis. The possible use of saliva as a diagnostic tool has been explored in several oral and systemic diseases. The use of proteomics for personalized medicine is a rapidly emerging field. (2) Salivary proteomic data of 36 healthy controls (HCs), 36 AIH and 36 PBC patients, obtained by liquid chromatography/mass spectrometry top-down pipeline, were analyzed by multiple Mann-Whitney test, Kendall correlation, Random Forest (RF) analysis and Linear Discriminant Analysis (LDA); (3) Mann-Whitney tests provided indications on the panel of differentially expressed salivary proteins and peptides, namely cystatin A, statherin, histatin 3, histatin 5 and histatin 6, which were elevated in AIH patients with respect to both HCs and PBC patients, while S100A12, S100A9 short, cystatin S1, S2, SN and C showed varied levels in PBC with respect to HCs and/or AIH patients. RF analysis evidenced a panel of salivary proteins/peptides able to classify with good accuracy PBC vs. HCs (83.3%), AIH vs. HCs (79.9%) and PBC vs. AIH (80.2%); (4) RF appears to be an attractive machine-learning tool suited for classification of AIH and PBC based on their different salivary proteomic profiles.

Development of an interpretable machine learning model associated with heavy metals' exposure to identify coronary heart disease among US adults via SHAP: Findings of the US NHANES from 2003 to 2018

Limited information is available on the links between heavy metals' exposure and coronary heart disease (CHD). We aim to establish an efficient and explainable machine learning (ML) model that associates heavy metals' exposure with CHD identification. Our datasets for investigating the associations between heavy metals and CHD were sourced from the US National Health and Nutrition Examination Survey (US NHANES, 2003-2018). Five ML models were established to identify CHD by heavy metals' exposure. Further, 11 discrimination characteristics were used to test the strength of the models. The optimally performing model was selected for identification. Finally, the SHapley Additive exPlanations (SHAP) tool was used for interpreting the features to visualize the selected model's decision-making capacity. In total, 12,554 participants were eligible for this study. The best performing random forest classifier (RF) based on 13 heavy metals to identify CHD was chosen (AUC: 0.827; 95%CI: 0.777-0.877; accuracy: 95.9%). SHAP values indicated that cesium (1.62), thallium (1.17), antimony (1.63), dimethylarsonic acid (0.91), barium (0.76), arsenous acid (0.79), total arsenic (0.01) in urine, and lead (3.58) and cadmium (4.66) in blood positively contributed to the model, while cobalt (-0.15), cadmium (-2.93), and uranium (-0.13) in urine negatively contributed to the model. The RF model was efficient, accurate, and robust in identifying an association between heavy metals' exposure and CHD among US NHANES 2003-2018 participants. Cesium, thallium, antimony, dimethylarsonic acid, barium, arsenous acid, and total arsenic in urine, and lead and cadmium in blood show positive relationships with CHD, while cobalt, cadmium, and uranium in urine show negative relationships with CHD.

Identification of NETs-related biomarkers and molecular clusters in systemic lupus erythematosus

Neutrophil extracellular traps (NETs) is an important process involved in the pathogenesis of systemic lupus erythematosus (SLE), but the potential mechanisms of NETs contributing to SLE at the genetic level have not been clearly investigated. This investigation aimed to explore the molecular characteristics of NETs-related genes (NRGs) in SLE based on bioinformatics analysis, and identify associated reliable biomarkers and molecular clusters. Dataset GSE45291 was acquired from the Gene Expression Omnibus repository and used as a training set for subsequent analysis. A total of 1006 differentially expressed genes (DEGs) were obtained, most of which were associated with multiple viral infections. The interaction of DEGs with NRGs revealed 8 differentially expressed NRGs (DE-NRGs). The correlation and protein-protein interaction analyses of these DE-NRGs were performed. Among them, HMGB1, ITGB2, and CREB5 were selected as hub genes by random forest, support vector machine, and least absolute shrinkage and selection operator algorithms. The significant diagnostic value for SLE was confirmed in the training set and three validation sets (GSE81622, GSE61635, and GSE122459). Additionally, three NETs-related sub-clusters were identified based on the hub genes' expression profiles analyzed by unsupervised consensus cluster assessment. Functional enrichment was performed among the three NETs subgroups, and the data revealed that cluster 1 highly expressed DEGs were prevalent in innate immune response pathways while that of cluster 3 were enriched in adaptive immune response pathways. Moreover, immune infiltration analysis also revealed that innate immune cells were markedly infiltrated in cluster 1 while the adaptive immune cells were upregulated in cluster 3. As per our knowledge, this investigation is the first to explore the molecular characteristics of NRGs in SLE, identify three potential biomarkers (HMGB1, ITGB2, and CREB5), and three distinct clusters based on these hub biomarkers.

Using machine learning to impact on long-term clinical care: principles, challenges, and practicalities

The rise of machine learning in healthcare has significant implications for paediatrics. Long-term conditions with significant disease heterogeneity comprise large portions of the routine work performed by paediatricians. Improving outcomes through discovery of disease and treatment prediction models, alongside novel subgroup clustering of patients, are some of the areas in which machine learning holds significant promise. While artificial intelligence has percolated into routine use in our day to day lives through advertising algorithms, song or movie selections and sifting of spam emails, the ability of machine learning to utilise highly complex and dimensional data has not yet reached its full potential in healthcare. In this review article, we discuss some of the foundations of machine learning, including some of the basic algorithms. We emphasise the importance of correct utilisation of machine learning, including adequate data preparation and external validation. Using nutrition in preterm infants and paediatric inflammatory bowel disease as examples, we discuss the evidence and potential utility of machine learning in paediatrics. Finally, we review some of the future applications, alongside challenges and ethical considerations related to application of artificial intelligence. IMPACT: Machine learning is a widely used term; however, understanding of the process and application to healthcare is lacking. This article uses clinical examples to explore complex machine learning terms and algorithms. We discuss limitations and potential future applications within paediatrics and neonatal medicine.

Artificial Intelligence in Inflammatory Bowel Disease Endoscopy: Advanced Development and New Horizons

Inflammatory bowel disease (IBD) is a complex chronic immune disease with two subtypes: Crohn's disease and ulcerative colitis. Considering the differences in pathogenesis, etiology, clinical presentation, and response to therapy among patients, gastroenterologists mainly rely on endoscopy to diagnose and treat IBD during clinical practice. However, as exemplified by the increasingly comprehensive ulcerative colitis endoscopic scoring system, the endoscopic diagnosis, evaluation, and treatment of IBD still rely on the subjective manipulation and judgment of endoscopists. In recent years, the use of artificial intelligence (AI) has grown substantially in various medical fields, and an increasing number of studies have investigated the use of this emerging technology in the field of gastroenterology. Clinical applications of AI have focused on IBD pathogenesis, etiology, diagnosis, and patient prognosis. Large-scale datasets offer tremendous utility in the development of novel tools to address the unmet clinical and practice needs for treating patients with IBD. However, significant differences among AI methodologies, datasets, and clinical findings limit the incorporation of AI technology into clinical practice. In this review, we discuss practical AI applications in the diagnosis of IBD via gastroenteroscopy and speculate regarding a future in which AI technology provides value for the diagnosis and treatment of IBD patients.

MLcps: machine learning cumulative performance score for classification problems

BACKGROUND

Assessing the performance of machine learning (ML) models requires careful consideration of the evaluation metrics used. It is often necessary to utilize multiple metrics to gain a comprehensive understanding of a trained model's performance, as each metric focuses on a specific aspect. However, comparing the scores of these individual metrics for each model to determine the best-performing model can be time-consuming and susceptible to subjective user preferences, potentially introducing bias.

RESULTS

We propose the Machine Learning Cumulative Performance Score (MLcps), a novel evaluation metric for classification problems. MLcps integrates several precomputed evaluation metrics into a unified score, enabling a comprehensive assessment of the trained model's strengths and weaknesses. We tested MLcps on 4 publicly available datasets, and the results demonstrate that MLcps provides a holistic evaluation of the model's robustness, ensuring a thorough understanding of its overall performance.

CONCLUSIONS

By utilizing MLcps, researchers and practitioners no longer need to individually examine and compare multiple metrics to identify the best-performing models. Instead, they can rely on a single MLcps value to assess the overall performance of their ML models. This streamlined evaluation process saves valuable time and effort, enhancing the efficiency of model evaluation. MLcps is available as a Python package at https://pypi.org/project/MLcps/.

Classification of multiple sclerosis clinical profiles using machine learning and grey matter connectome

Purpose: The main goal of this study is to investigate the discrimination power of Grey Matter (GM) thickness connectome data between Multiple Sclerosis (MS) clinical profiles using statistical and Machine Learning (ML) methods.

Materials and Methods: A dataset composed of 90 MS patients acquired at the MS clinic of Lyon Neurological Hospital was used for the analysis. Four MS profiles were considered, corresponding to Clinical Isolated Syndrome (CIS), Relapsing-Remitting MS (RRMS), Secondary Progressive MS (SPMS), and Primary Progressive MS (PPMS). Each patient was classified in one of these profiles by our neurologist and underwent longitudinal MRI examinations including T1-weighted image acquisition at each examination, from which the GM tissue was segmented and the cortical GM thickness measured. Following the GM parcellation using two different atlases (FSAverage and Glasser 2016), the morphological connectome was built and six global metrics (Betweenness Centrality (BC), Assortativity (r), Transitivity (T), Efficiency (E_g), Modularity (Q) and Density (D)) were extracted. Based on their connectivity metrics, MS profiles were first statistically compared and second, classified using four different learning machines (Logistic Regression, Random Forest, Support Vector Machine and AdaBoost), combined in a higher level ensemble model by majority voting. Finally, the impact of the GM spatial resolution on the MS clinical profiles classification was analyzed.

Results: Using binary comparisons between the four MS clinical profiles, statistical differences and classification performances higher than 0.7 were observed. Good performances were obtained when comparing the two early clinical forms, RRMS and PPMS (F1 score of 0.86), and the two neurodegenerative profiles, PPMS and SPMS (F1 score of 0.72). When comparing the two atlases, slightly better performances were obtained with the Glasser 2016 atlas, especially between RRMS with PPMS (F1 score of 0.83), compared to the FSAverage atlas (F1 score of 0.69). Also, the thresholding value for graph binarization was investigated suggesting more informative graph properties in the percentile range between 0.6 and 0.8.

Conclusion: An automated pipeline was proposed for the classification of MS clinical profiles using six global graph metrics extracted from the GM morphological connectome of MS patients. This work demonstrated that GM morphological connectivity data could provide good classification performances by combining four simple ML models, without the cost of long and complex MR techniques, such as MR diffusion, and/or deep learning architectures.

Prediction of Crohn's Disease Stricturing Phenotype Using a NOD2-derived Genomic Biomarker

BACKGROUND

Crohn's disease (CD) is highly heterogenous and may be complicated by stricturing behavior. Personalized prediction of stricturing will inform management. We aimed to create a stricturing risk stratification model using genomic/clinical data.

METHODS

Exome sequencing was performed on CD patients, and phenotype data retrieved. Biallelic variants in NOD2 were identified. NOD2 was converted into a per-patient deleteriousness metric ("GenePy"). Using training data, patients were stratified into risk groups for fibrotic stricturing using NOD2. Findings were validated in a testing data set. Models were modified to include disease location at diagnosis. Cox proportional hazards assessed performance.

RESULTS

Six hundred forty-five patients were included (373 children and 272 adults); 48 patients fulfilled criteria for monogenic NOD2-related disease (7.4%), 24 of whom had strictures. NOD2 GenePy scores stratified patients in training data into 2 risk groups. Within testing data, 30 of 161 patients (18.6%) were classified as high-risk based on the NOD2 biomarker, with stricturing in 17 of 30 (56.7%). In the low-risk group, 28 of 131 (21.4%) had stricturing behavior. Cox proportional hazards using the NOD2 risk groups demonstrated a hazard ratio (HR) of 2.092 (P = 2.4 × 10-5), between risk groups. Limiting analysis to patients diagnosed aged < 18-years improved performance (HR-3.164, P = 1 × 10-6). Models were modified to include disease location, such as terminal ileal (TI) disease or not. Inclusion of NOD2 risk groups added significant additional utility to prediction models. High-risk group pediatric patients presenting with TI disease had a HR of 4.89 (P = 2.3 × 10-5) compared with the low-risk group patients without TI disease.

CONCLUSIONS

A NOD2 genomic biomarker predicts stricturing risk, with prognostic power improved in pediatric-onset CD. Implementation into a clinical setting can help personalize management.

Computer‐Assisted Image Analysis in Assessment of Peripheral Joint MRI in Inflammatory Arthritis: A Systematic Review and Meta‐analysis

Objective

To summarize the feasibility of computer‐assisted quantification of joint pathologies on magnetic resonance imaging (MRI) in patients with inflammatory arthritis by evaluating the published data on reliability, validity, and feasibility.

Methods

A systematic literature search was performed for original articles published from January 1, 1985, to January 1, 2021. We selected studies in which patients with inflammatory arthritis were enrolled, and arthritis‐related structural damage/synovitis in peripheral joints was assessed on non‐contrast‐enhanced, contrast‐enhanced (CE), or dynamic CE (DCE)‐MRI using (semi)automated methods. Data were pooled using random‐effects model.

Results

Twenty‐eight studies consisting of 1342 MRIs were included (mean age, 54.8 years; 66.7% female; duration of arthritis, 3.6 years). Among clinical/laboratory factors, synovial membrane volume (SV) was moderately correlated with erthrocyte sedimentation rate (ESR) level (P < 0.01). Pooled analysis showed an overall excellent intra‐ and inter‐reader reliability for computer‐aided quantification of bone erosion volume (BEV; r = 0.97 [95% CI: 0.92‐0.99], 0.93 [0.87‐0.97]), SV (r = 0.98 [95% CI: 0.90‐0.99], 0.86 [0.78‐0.91]), and DCE‐MRI perfusion parameters (r = 0.96‐0.99). Meta‐regression showed that computer‐aided and manual methods provide comparable reliability (P > 0.05). Computer‐aided measurement of BEV (r = 0.92), SV (r = 0.82), and DCE‐MRI biomarkers (r = 0.72 N‐total; r = 0.74 N‐plateau; r = 0.64 N‐washout) were significantly correlated with the Rheumatoid Arthritis Magnetic Resonance Imaging Score (RAMRIS; P < 0.01), allowing for earlier assessment of drug efficacy. On average, (semi)automated analysis of BEV/SV took 17 minutes (vs. 9 minutes for the RAMRIS) and DCE‐MRI took 4 minutes (vs. 33 minutes for manual assessment).

Conclusion

Computer‐aided image quantification technologies demonstrate excellent reliability and validity when used to quantify MRI pathologies of peripheral joints in patients with inflammatory arthritis. Computer‐aided evaluation of inflammatory arthritis is an emerging field and should be considered as a viable complement to conventional observer‐based scoring methods for clinical trials application.

Prediction models used in the progression of chronic kidney disease: A scoping review

Objective

To provide a review of prediction models that have been used to measure clinical or pathological progression of chronic kidney disease (CKD).

Design

Scoping review.

Data sources

Medline, EMBASE, CINAHL and Scopus from the year 2011 to 17th February 2022.

Study selection

All English written studies that are published in peer-reviewed journals in any country, that developed at least a statistical or computational model that predicted the risk of CKD progression.

Data extraction

Eligible studies for full text review were assessed on the methods that were used to predict the progression of CKD. The type of information extracted included: the author(s), title of article, year of publication, study dates, study location, number of participants, study design, predicted outcomes, type of prediction model, prediction variables used, validation assessment, limitations and implications.

Results

From 516 studies, 33 were included for full-text review. A qualitative analysis of the articles was compared following the extracted information. The study populations across the studies were heterogenous and data acquired by the studies were sourced from different levels and locations of healthcare systems. 31 studies implemented supervised models, and 2 studies included unsupervised models. Regardless of the model used, the predicted outcome included measurement of risk of progression towards end-stage kidney disease (ESKD) of related definitions, over given time intervals. However, there is a lack of reporting consistency on details of the development of their prediction models.

Conclusions

Researchers are working towards producing an effective model to provide key insights into the progression of CKD. This review found that cox regression modelling was predominantly used among the small number of studies in the review. This made it difficult to perform a comparison between ML algorithms, more so when different validation methods were used in different cohort types. There needs to be increased investment in a more consistent and reproducible approach for future studies looking to develop risk prediction models for CKD progression.

Autoimmune Disease Classification Based on PubMed Text Mining

Autoimmune diseases (AIDs) are often co-associated, and about 25% of patients with one AID tend to develop other comorbid AIDs. Here, we employ the power of datamining to predict the comorbidity of AIDs based on their normalized co-citation in PubMed. First, we validate our technique in a test dataset using earlier-reported comorbidities of seven knowns AIDs. Notably, the prediction correlates well with comorbidity (R = 0.91) and validates our methodology. Then, we predict the association of 100 AIDs and classify them using principal component analysis. Our results are helpful in classifying AIDs into one of the following systems: (1) gastrointestinal, (2) neuronal, (3) eye, (4) cutaneous, (5) musculoskeletal, (6) kidneys and lungs, (7) cardiovascular, (8) hematopoietic, (9) endocrine, and (10) multiple. Our classification agrees with experimentally based taxonomy and ranks AID according to affected systems and gender. Some AIDs are unclassified and do not associate well with other AIDs. Interestingly, Alzheimer’s disease correlates well with other AIDs such as multiple sclerosis. Finally, our results generate a network classification of autoimmune diseases based on PubMed text mining and help map this medical universe. Our results are expected to assist healthcare workers in diagnosing comorbidity in patients with an autoimmune disease, and to help researchers in identifying common genetic, environmental, and autoimmune mechanisms.

Recent Application of Artificial Intelligence in Non-Gynecological Cancer Cytopathology: A Systematic Review

Simple Summary

Artificial intelligence (AI) has attracted significant interest in the healthcare sector due to its promising results. Cytological examination is a critical step in the initial diagnosis of cancer. Here, we conducted a systematic review with quantitative analysis to understand the current status of AI applications in non-gynecological (non-GYN) cancer cytology. In our analysis, we found that most of the studies focused on classification and segmentation tasks. Overall, AI showed promising results for non-GYN cancer cytopathology analysis. However, the lack of well-annotated, large-scale datasets with Z-stacking and external cross-validation was the major limitation across all studies.

Abstract

State-of-the-art artificial intelligence (AI) has recently gained considerable interest in the healthcare sector and has provided solutions to problems through automated diagnosis. Cytological examination is a crucial step in the initial diagnosis of cancer, although it shows limited diagnostic efficacy. Recently, AI applications in the processing of cytopathological images have shown promising results despite the elementary level of the technology. Here, we performed a systematic review with a quantitative analysis of recent AI applications in non-gynecological (non-GYN) cancer cytology to understand the current technical status. We searched the major online databases, including MEDLINE, Cochrane Library, and EMBASE, for relevant English articles published from January 2010 to January 2021. The searched query terms were: “artificial intelligence”, “image processing”, “deep learning”, “cytopathology”, and “fine-needle aspiration cytology.” Out of 17,000 studies, only 26 studies (26 models) were included in the full-text review, whereas 13 studies were included for quantitative analysis. There were eight classes of AI models treated of according to target organs: thyroid (n = 11, 39%), urinary bladder (n = 6, 21%), lung (n = 4, 14%), breast (n = 2, 7%), pleural effusion (n = 2, 7%), ovary (n = 1, 4%), pancreas (n = 1, 4%), and prostate (n = 1, 4). Most of the studies focused on classification and segmentation tasks. Although most of the studies showed impressive results, the sizes of the training and validation datasets were limited. Overall, AI is also promising for non-GYN cancer cytopathology analysis, such as pathology or gynecological cytology. However, the lack of well-annotated, large-scale datasets with Z-stacking and external cross-validation was the major limitation found across all studies. Future studies with larger datasets with high-quality annotations and external validation are required.

Artificial Intelligence in Rheumatoid Arthritis: Current Status and Future Perspectives: A State-of-the-Art Review

Investigation of the potential applications of artificial intelligence (AI), including machine learning (ML) and deep learning (DL) techniques, is an exponentially growing field in medicine and healthcare. These methods can be critical in providing high-quality care to patients with chronic rheumatological diseases lacking an optimal treatment, like rheumatoid arthritis (RA), which is the second most prevalent autoimmune disease. Herein, following reviewing the basic concepts of AI, we summarize the advances in its applications in RA clinical practice and research. We provide directions for future investigations in this field after reviewing the current knowledge gaps and technical and ethical challenges in applying AI. Automated models have been largely used to improve RA diagnosis since the early 2000s, and they have used a wide variety of techniques, e.g., support vector machine, random forest, and artificial neural networks. AI algorithms can facilitate screening and identification of susceptible groups, diagnosis using omics, imaging, clinical, and sensor data, patient detection within electronic health record (EHR), i.e., phenotyping, treatment response assessment, monitoring disease course, determining prognosis, novel drug discovery, and enhancing basic science research. They can also aid in risk assessment for incidence of comorbidities, e.g., cardiovascular diseases, in patients with RA. However, the proposed models may vary significantly in their performance and reliability. Despite the promising results achieved by AI models in enhancing early diagnosis and management of patients with RA, they are not fully ready to be incorporated into clinical practice. Future investigations are required to ensure development of reliable and generalizable algorithms while they carefully look for any potential source of bias or misconduct. We showed that a growing body of evidence supports the potential role of AI in revolutionizing screening, diagnosis, and management of patients with RA. However, multiple obstacles hinder clinical applications of AI models. Incorporating the machine and/or deep learning algorithms into real-world settings would be a key step in the progress of AI in medicine.

Utility of support vector machine and decision tree to identify the prognosis of metformin poisoning in the United States: analysis of National Poisoning Data System

BACKGROUND

With diabetes incidence growing globally and metformin still being the first-line for its treatment, metformin's toxicity and overdose have been increasing. Hence, its mortality rate is increasing. For the first time, we aimed to study the efficacy of machine learning algorithms in predicting the outcome of metformin poisoning using two well-known classification methods, including support vector machine (SVM) and decision tree (DT).

METHODS

This study is a retrospective cohort study of National Poison Data System (NPDS) data, the largest data repository of poisoning cases in the United States. The SVM and DT algorithms were developed using training and test datasets. We also used precision-recall and ROC curves and Area Under the Curve value (AUC) for model evaluation.

RESULTS

Our model showed that acidosis, hypoglycemia, electrolyte abnormality, hypotension, elevated anion gap, elevated creatinine, tachycardia, and renal failure are the most important determinants in terms of outcome prediction of metformin poisoning. The average negative predictive value for the decision tree and SVM models was 92.30 and 93.30. The AUC of the ROC curve of the decision tree for major, minor, and moderate outcomes was 0.92, 0.92, and 0.89, respectively. While this figure of SVM model for major, minor, and moderate outcomes was 0.98, 0.90, and 0.82, respectively.

CONCLUSIONS

In order to predict the prognosis of metformin poisoning, machine learning algorithms might help clinicians in the management and follow-up of metformin poisoning cases.

Artificial intelligence and thyroid disease management

Artificial intelligence (AI) is transforming healthcare and offers new tools in clinical research, personalized medicine, and medical diagnostics. Thyroid function tests represent an important asset for physicians in the diagnosis and monitoring of pathologies. Artificial intelligence tools can clearly assist physicians and specialists in laboratory medicine to optimize test prescription, tests interpretation, decision making, process optimization, and assay design. Our article is reviewing several of these aspects. As thyroid AI models rely on large data sets, which often requires distributed learning from multi-center contributions, this article also briefly discusses this issue.