Machine-learning based lipid mediator serum concentration patterns allow identification of multiple sclerosis patients with high accuracy

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

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

Dysregulated lipid metabolism networks modulate T-cell function in people with relapsing-remitting multiple sclerosis

Altered cholesterol, oxysterol, sphingolipid, and fatty acid concentrations are reported in blood, cerebrospinal fluid, and brain tissue of people with relapsing-remitting multiple sclerosis (RRMS) and are linked to disease progression and treatment responses. CD4 + T cells are pathogenic in RRMS, and defective T-cell function could be mediated in part by liver X receptors (LXRs)-nuclear receptors that regulate lipid homeostasis and immunity. RNA-sequencing and pathway analysis identified that genes within the 'lipid metabolism' and 'signalling of nuclear receptors' pathways were dysregulated in CD4 + T cells isolated from RRMS patients compared with healthy donors. While LXRB and genes associated with cholesterol metabolism were upregulated, other T-cell LXR-target genes, including genes involved in cellular lipid uptake (inducible degrader of the LDL receptor, IDOL), and the rate-limiting enzyme for glycosphingolipid biosynthesis (UDP-glucosylceramide synthase, UGCG) were downregulated in T cells from patients with RRMS compared to healthy donors. Correspondingly, plasma membrane glycosphingolipids were reduced, and cholesterol levels increased in RRMS CD4 + T cells, an effect partially recapitulated in healthy T cells by in vitro culture with T-cell receptor stimulation in the presence of serum from RRMS patients. Notably, stimulation with LXR-agonist GW3965 normalized membrane cholesterol levels, and reduced proliferation and IL17 cytokine production in RRMS CD4 + T-cells. Thus, LXR-mediated lipid metabolism pathways were dysregulated in T cells from patients with RRMS and could contribute to RRMS pathogenesis. Therapies that modify lipid metabolism could help restore immune cell function.

Diet Supplemented with Special Formula Milk Powder Promotes the Growth of the Brain in Rats

This investigation was to study the effects of different formula components on the brain growth of rats. Fifty male SD rats were randomly divided into five groups: a basic diet group; a 20% ordinary milk powder group; a 20% special milk powder group; a 30% ordinary milk powder group; and a 30% special milk powder group by weight. LC-MS was used to detect brain lipidomics. After 28 days of feeding, compared with the basic diet group, the brain/body weights of rats in the 30% ordinary milk powder group were increased. The serum levels of 5-HIAA in the 30% ordinary milk powder group were lower than in the 20% ordinary milk powder group. Compared with the basic diet group, the expressions of DLCL, MePC, PI, and GM1 were higher in the groups with added special milk powder, while the expressions of LPE, LdMePE, SM, and MGTG were higher in the groups with added ordinary milk powder. The expression of MBP was significantly higher in the 20% ordinary group. This study found that different formula components of infant milk powder could affect brain growth in SD rats. The addition of special formula infant milk powder may have beneficial effects on rat brains by regulating brain lipid expression.

Blood metabolomic and transcriptomic signatures stratify patient subgroups in multiple sclerosis according to disease severity

There are no blood-based biomarkers distinguishing patients with relapsing-remitting (RRMS) from secondary progressive multiple sclerosis (SPMS) although evidence supports metabolomic changes according to MS disease severity. Here machine learning analysis of serum metabolomic data stratified patients with RRMS from SPMS with high accuracy and a putative score was developed that stratified MS patient subsets. The top differentially expressed metabolites between SPMS versus patients with RRMS included lipids and fatty acids, metabolites enriched in pathways related to cellular respiration, notably, elevated lactate and glutamine (gluconeogenesis-related) and acetoacetate and bOHbutyrate (ketone bodies), and reduced alanine and pyruvate (glycolysis-related). Serum metabolomic changes were recapitulated in the whole blood transcriptome, whereby differentially expressed genes were also enriched in cellular respiration pathways in patients with SPMS. The final gene-metabolite interaction network demonstrated a potential metabolic shift from glycolysis toward increased gluconeogenesis and ketogenesis in SPMS, indicating metabolic stress which may trigger stress response pathways and subsequent neurodegeneration.

Plasma Lipidomic Profiling Using Mass Spectrometry for Multiple Sclerosis Diagnosis and Disease Activity Stratification (LipidMS)

This investigation explores the potential of plasma lipidomic signatures for aiding in the diagnosis of Multiple Sclerosis (MS) and evaluating the clinical course and disease activity of diseased patients. Plasma samples from 60 patients with MS (PwMS) were clinically stratified to either a relapsing-remitting (RRMS) or a chronic progressive MS course and 60 age-matched controls were analyzed using state-of-the-art direct infusion quantitative shotgun lipidomics. To account for potential confounders, data were filtered for age and BMI correlations. The statistical analysis employed supervised and unsupervised multivariate data analysis techniques, including a principal component analysis (PCA), a partial least squares discriminant analysis (oPLS-DA) and a random forest (RF). To determine whether the significant absolute differences in the lipid subspecies have a relevant effect on the overall composition of the respective lipid classes, we introduce a class composition visualization (CCV). We identified 670 lipids across 16 classes. PwMS showed a significant increase in diacylglycerols (DAG), with DAG 16:0;0_18:1;0 being proven to be the lipid with the highest predictive ability for MS as determined by RF. The alterations in the phosphatidylethanolamines (PE) were mainly linked to RRMS while the alterations in the ether-bound PEs (PE O-) were found in chronic progressive MS. The amount of CE species was reduced in the CPMS cohort whereas TAG species were reduced in the RRMS patients, both lipid classes being relevant in lipid storage. Combining the above mentioned data analyses, distinct lipidomic signatures were isolated and shown to be correlated with clinical phenotypes. Our study suggests that specific plasma lipid profiles are not merely associated with the diagnosis of MS but instead point toward distinct clinical features in the individual patient paving the way for personalized therapy and an enhanced understanding of MS pathology.

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.

Recursive computed ABC (cABC) analysis as a precise method for reducing machine learning based feature sets to their minimum informative size

Selecting the k best features is a common task in machine learning. Typically, a few features have high importance, but many have low importance (right-skewed distribution). This report proposes a numerically precise method to address this skewed feature importance distribution in order to reduce a feature set to the informative minimum of items. Computed ABC analysis (cABC) is an item categorization method that aims to identify the most important items by partitioning a set of non-negative numerical items into subsets "A", "B", and "C" such that subset "A" contains the "few important" items based on specific properties of ABC curves defined by their relationship to Lorenz curves. In its recursive form, the cABC analysis can be applied again to subset "A". A generic image dataset and three biomedical datasets (lipidomics and two genomics datasets) with a large number of variables were used to perform the experiments. The experimental results show that the recursive cABC analysis limits the dimensions of the data projection to a minimum where the relevant information is still preserved and directs the feature selection in machine learning to the most important class-relevant information, including filtering feature sets for nonsense variables. Feature sets were reduced to 10% or less of the original variables and still provided accurate classification in data not used for feature selection. cABC analysis, in its recursive variant, provides a computationally precise means of reducing information to a minimum. The minimum is the result of a computation of the number of k most relevant items, rather than a decision to select the k best items from a list. In addition, there are precise criteria for stopping the reduction process. The reduction to the most important features can improve the human understanding of the properties of the data set. The cABC method is implemented in the Python package "cABCanalysis" available at https://pypi.org/project/cABCanalysis/ .

ATR-FTIR spectroscopy of plasma supported by multivariate analysis discriminates multiple sclerosis disease

Multiple sclerosis (MS) is one of the most common neurodegenerative diseases showing various symptoms both of physical and cognitive type. In this work, we used attenuated total reflection Fourier transformed infrared (ATR-FTIR) spectroscopy to analyze plasma samples for discriminating MS patients from healthy control individuals, and identifying potential spectral biomarkers helping the diagnosis through a quick non-invasive blood test. The cohort of the study consists of 85 subjects, including 45 MS patients and 40 healthy controls. The differences in the spectral features both in the fingerprint region (1800-900 cm^-1) and in the high region (3050-2800 cm^-1) of the infrared spectra were highlighted also with the support of different chemometric methods, to capture the most significant wavenumbers for the differentiation. The results show an increase in the lipid/protein ratio in MS patients, indicating changes in the level (metabolism) of these molecular components in the plasma. Moreover, the multivariate tools provided a promising rate of success in the diagnosis, with 78% sensitivity and 83% specificity obtained through the random forest model in the fingerprint region. The MS diagnostic tools based on biomarkers identification on blood (and blood component, like plasma or serum) are very challenging and the specificity and sensitivity values obtained in this work are very encouraging. Overall, the results obtained suggest that ATR-FTIR spectroscopy on plasma samples, requiring minimal or no manipulation, coupled with statistical multivariate approaches, is a promising analytical tool to support MS diagnosis through the identification of spectral biomarkers.

Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis

BACKGROUND

The expansion of the availability of advanced imaging methods needs more time, expertise, and resources which is in contrast to the primary goal of the imaging techniques. To overcome most of these difficulties, artificial intelligence (AI) can be used. A number of studies used AI models for multiple sclerosis (MS) diagnosis and reported diverse results. Therefore, we aim to perform a comprehensive systematic review and meta-analysis study on the role of AI in the diagnosis of MS.

METHODS

We performed a systematic search using four databases including PubMed, Scopus, Web of Science, and IEEE. Studies that applied deep learning or AI to the diagnosis of MS based on any modalities were considered eligible in our study. The accuracy, sensitivity, specificity, precision, and area under curve (AUC) were pooled with a random-effects model and 95% confidence interval (CI).

RESULTS

After the screening, 41 articles with 5989 individuals met the inclusion criteria and were included in our qualitative and quantitative synthesis. Our analysis showed that the overall accuracy among studies was 94% (95%CI: 93%, 96%). The pooled sensitivity and specificity were 92% (95%CI: 90%, 95%) and 93% (95%CI: 90%, 96%), respectively. Furthermore, our analysis showed 92% precision in MS diagnosis for AI studies (95%CI: 88%, 97%). Also, the overall pooled AUC was 93% (95%CI: 89%, 96%).

CONCLUSION

Overall, AI models can further improve our diagnostic practice in MS patients. Our results indicate that the use of AI can aid the clinicians in accurate diagnosis of MS and improve current diagnostic approaches as most of the parameters including accuracy, sensitivity, specificity, precision, and AUC were considerably high, especially when using MRI data.

Endocannabinoid levels in peripheral blood mononuclear cells of multiple sclerosis patients treated with dimethyl fumarate

The endocannabinoid system (ECS), a signalling network with immunomodulatory properties, is a potential therapeutic target in multiple sclerosis (MS). Dimethyl fumarate (DMF) is an approved drug for MS whose mechanism of action has not been fully elucidated; the possibility exists that its therapeutic effects could imply the ECS. With the aim of studying if DMF can modulate the ECS, the endocannabinoids 2-arachidonoylglycerol (2-AG), anandamide (AEA), oleoylethanolamide (OEA) and palmitoylethanolamide (PEA) were determined by liquid chromatography-mass spectrometry in peripheral blood mononuclear cells from 21 healthy donors (HD) and 32 MS patients at baseline and after 12 and 24 months of DMF treatment. MS patients presented lower levels of 2-AG and PEA compared to HD. 2-AG increased at 24 months, reaching HD levels. AEA and PEA remained stable at 12 and 24 months. OEA increased at 12 months and returned to initial levels at 24 months. Patients who achieved no evidence of disease activity (NEDA3) presented the same modulation over time as EDA3 patients. PEA was modulated differentially between females and males. Our results show that the ECS is dysregulated in MS patients. The increase in 2-AG and OEA during DMF treatment suggests a possible role of DMF in ECS modulation.

Robust Classification Using Posterior Probability Threshold Computation Followed by Voronoi Cell Based Class Assignment Circumventing Pitfalls of Bayesian Analysis of Biomedical Data

Bayesian inference is ubiquitous in science and widely used in biomedical research such as cell sorting or “omics” approaches, as well as in machine learning (ML), artificial neural networks, and “big data” applications. However, the calculation is not robust in regions of low evidence. In cases where one group has a lower mean but a higher variance than another group, new cases with larger values are implausibly assigned to the group with typically smaller values. An approach for a robust extension of Bayesian inference is proposed that proceeds in two main steps starting from the Bayesian posterior probabilities. First, cases with low evidence are labeled as “uncertain” class membership. The boundary for low probabilities of class assignment (threshold ε) is calculated using a computed ABC analysis as a data-based technique for item categorization. This leaves a number of cases with uncertain classification (p < ε). Second, cases with uncertain class membership are relabeled based on the distance to neighboring classified cases based on Voronoi cells. The approach is demonstrated on biomedical data typically analyzed with Bayesian statistics, such as flow cytometric data sets or biomarkers used in medical diagnostics, where it increased the class assignment accuracy by 1−10% depending on the data set. The proposed extension of the Bayesian inference of class membership can be used to obtain robust and plausible class assignments even for data at the extremes of the distribution and/or for which evidence is weak.

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), which can lead to brain, spinal cord, and optic nerve problems. A total of 2.8 million are estimated to suffer from MS. Globally, a new case of MS is reported every five minutes. In this review, we discuss the proposed approaches to diagnosing MS using machine learning (ML) published between 2011 and 2022. Numerous models have been developed using different types of data, including magnetic resonance imaging (MRI) and clinical data. We identified the methods that achieved the best results in diagnosing MS. The most implemented approaches are SVM, RF, and CNN. Moreover, we discussed the challenges and opportunities in MS diagnosis to improve AI systems to enable researchers and practitioners to enhance their approaches and improve the automated diagnosis of MS. The challenges faced by automated MS diagnosis include difficulty distinguishing the disease from other diseases showing similar symptoms, protecting the confidentiality of the patients' data, achieving reliable ML models that are also easily understood by non-experts, and the difficulty of collecting a large reliable dataset. Moreover, we discussed several opportunities in the field such as the implementation of secure platforms, employing better AI solutions, developing better disease prognosis systems, combining more than one data type for better MS prediction and using OCT data for diagnosis, utilizing larger, multi-center datasets to improve the reliability of the developed models, and commercialization.

The role of machine learning in developing non-magnetic resonance imaging based biomarkers for multiple sclerosis: a systematic review

Background

Multiple sclerosis (MS) is a neurological condition whose symptoms, severity, and progression over time vary enormously among individuals. Ideally, each person living with MS should be provided with an accurate prognosis at the time of diagnosis, precision in initial and subsequent treatment decisions, and improved timeliness in detecting the need to reassess treatment regimens. To manage these three components, discovering an accurate, objective measure of overall disease severity is essential. Machine learning (ML) algorithms can contribute to finding such a clinically useful biomarker of MS through their ability to search and analyze datasets about potential biomarkers at scale. Our aim was to conduct a systematic review to determine how, and in what way, ML has been applied to the study of MS biomarkers on data from sources other than magnetic resonance imaging.

Methods

Systematic searches through eight databases were conducted for literature published in 2014–2020 on MS and specified ML algorithms.

Results

Of the 1, 052 returned papers, 66 met the inclusion criteria. All included papers addressed developing classifiers for MS identification or measuring its progression, typically, using hold-out evaluation on subsets of fewer than 200 participants with MS. These classifiers focused on biomarkers of MS, ranging from those derived from omics and phenotypical data (34.5% clinical, 33.3% biological, 23.0% physiological, and 9.2% drug response). Algorithmic choices were dependent on both the amount of data available for supervised ML (91.5%; 49.2% classification and 42.3% regression) and the requirement to be able to justify the resulting decision-making principles in healthcare settings. Therefore, algorithms based on decision trees and support vector machines were commonly used, and the maximum average performance of 89.9% AUC was found in random forests comparing with other ML algorithms.

Conclusions

ML is applicable to determining how candidate biomarkers perform in the assessment of disease severity. However, applying ML research to develop decision aids to help clinicians optimize treatment strategies and analyze treatment responses in individual patients calls for creating appropriate data resources and shared experimental protocols. They should target proceeding from segregated classification of signals or natural language to both holistic analyses across data modalities and clinically-meaningful differentiation of disease.

Role of artificial intelligence in MS clinical practice

•

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

•

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

•

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

•

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

•

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

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

Machine Learning and Pathway Analysis-Based Discovery of Metabolomic Markers Relating to Chronic Pain Phenotypes

Recent scientific evidence suggests that chronic pain phenotypes are reflected in metabolomic changes. However, problems associated with chronic pain, such as sleep disorders or obesity, may complicate the metabolome pattern. Such a complex phenotype was investigated to identify common metabolomics markers at the interface of persistent pain, sleep, and obesity in 71 men and 122 women undergoing tertiary pain care. They were examined for patterns in d = 97 metabolomic markers that segregated patients with a relatively benign pain phenotype (low and little bothersome pain) from those with more severe clinical symptoms (high pain intensity, more bothersome pain, and co-occurring problems such as sleep disturbance). Two independent lines of data analysis were pursued. First, a data-driven supervised machine learning-based approach was used to identify the most informative metabolic markers for complex phenotype assignment. This pointed primarily at adenosine monophosphate (AMP), asparagine, deoxycytidine, glucuronic acid, and propionylcarnitine, and secondarily at cysteine and nicotinamide adenine dinucleotide (NAD) as informative for assigning patients to clinical pain phenotypes. After this, a hypothesis-driven analysis of metabolic pathways was performed, including sleep and obesity. In both the first and second line of analysis, three metabolic markers (NAD, AMP, and cysteine) were found to be relevant, including metabolic pathway analysis in obesity, associated with changes in amino acid metabolism, and sleep problems, associated with downregulated methionine metabolism. Taken together, present findings provide evidence that metabolomic changes associated with co-occurring problems may play a role in the development of severe pain. Co-occurring problems may influence each other at the metabolomic level. Because the methionine and glutathione metabolic pathways are physiologically linked, sleep problems appear to be associated with the first metabolic pathway, whereas obesity may be associated with the second.

Machine-Learning Analysis of Serum Proteomics in Neuropathic Pain after Nerve Injury in Breast Cancer Surgery Points at Chemokine Signaling via SIRT2 Regulation

BACKGROUND

Persistent postsurgical neuropathic pain (PPSNP) can occur after intraoperative damage to somatosensory nerves, with a prevalence of 29-57% in breast cancer surgery. Proteomics is an active research field in neuropathic pain and the first results support its utility for establishing diagnoses or finding therapy strategies.

METHODS

57 women (30 non-PPSNP/27 PPSNP) who had experienced a surgeon-verified intercostobrachial nerve injury during breast cancer surgery, were examined for patterns in 74 serum proteomic markers that allowed discrimination between subgroups with or without PPSNP. Serum samples were obtained both before and after surgery.

RESULTS

Unsupervised data analyses, including principal component analysis and self-organizing maps of artificial neurons, revealed patterns that supported a data structure consistent with pain-related subgroup (non-PPSPN vs. PPSNP) separation. Subsequent supervised machine learning-based analyses revealed 19 proteins (CD244, SIRT2, CCL28, CXCL9, CCL20, CCL3, IL.10RA, MCP.1, TRAIL, CCL25, IL10, uPA, CCL4, DNER, STAMPB, CCL23, CST5, CCL11, FGF.23) that were informative for subgroup separation. In cross-validated training and testing of six different machine-learned algorithms, subgroup assignment was significantly better than chance, whereas this was not possible when training the algorithms with randomly permuted data or with the protein markers not selected. In particular, sirtuin 2 emerged as a key protein, presenting both before and after breast cancer treatments in the PPSNP compared with the non-PPSNP subgroup.

CONCLUSIONS

The identified proteins play important roles in immune processes such as cell migration, chemotaxis, and cytokine-signaling. They also have considerable overlap with currently known targets of approved or investigational drugs. Taken together, several lines of unsupervised and supervised analyses pointed to structures in serum proteomics data, obtained before and after breast cancer surgery, that relate to neuroinflammatory processes associated with the development of neuropathic pain after an intraoperative nerve lesion.

Autophagy activation, lipotoxicity and lysosomal membrane permeabilization synergize to promote pimozide- and loperamide-induced glioma cell death

Increasing evidence suggests that induction of lethal macroautophagy/autophagy carries potential significance for the treatment of glioblastoma (GBM). In continuation of previous work, we demonstrate that pimozide and loperamide trigger an ATG5- and ATG7 (autophagy related 5 and 7)-dependent type of cell death that is significantly reduced with cathepsin inhibitors and the lipid reactive oxygen species (ROS) scavenger α-tocopherol in MZ-54 GBM cells. Global proteomic analysis after treatment with both drugs also revealed an increase of proteins related to lipid and cholesterol metabolic processes. These changes were accompanied by a massive accumulation of cholesterol and other lipids in the lysosomal compartment, indicative of impaired lipid transport/degradation. In line with these observations, pimozide and loperamide treatment were associated with a pronounced increase of bioactive sphingolipids including ceramides, glucosylceramides and sphingoid bases measured by targeted lipidomic analysis. Furthermore, pimozide and loperamide inhibited the activity of SMPD1/ASM (sphingomyelin phosphodiesterase 1) and promoted induction of lysosomal membrane permeabilization (LMP), as well as release of CTSB (cathepsin B) into the cytosol in MZ-54 wild-type (WT) cells. Whereas LMP and cell death were significantly attenuated in ATG5 and ATG7 knockout (KO) cells, both events were enhanced by depletion of the lysophagy receptor VCP (valosin containing protein), supporting a pro-survival function of lysophagy under these conditions. Collectively, our data suggest that pimozide and loperamide-driven autophagy and lipotoxicity synergize to induce LMP and cell death. The results also support the notion that simultaneous overactivation of autophagy and induction of LMP represents a promising approach for the treatment of GBM.Abbreviations: ACD: autophagic cell death; AKT1: AKT serine/threonine kinase 1; ATG5: autophagy related 5; ATG7: autophagy related 7; ATG14: autophagy related 14; CERS1: ceramide synthase 1; CTSB: cathepsin B; CYBB/NOX2: cytochrome b-245 beta chain; ER: endoplasmatic reticulum; FBS: fetal bovine serum; GBM: glioblastoma; GO: gene ontology; HTR7/5-HT7: 5-hydroxytryptamine receptor 7; KD: knockdown; KO: knockout; LAMP1: lysosomal associated membrane protein 1; LAP: LC3-associated phagocytosis; LMP: lysosomal membrane permeabilization; MAP1LC3B: microtubule associated protein 1 light chain 3 beta; MTOR: mechanistic target of rapamycin kinase; RB1CC1: RB1 inducible coiled-coil 1; ROS: reactive oxygen species; RPS6: ribosomal protein S6; SMPD1/ASM: sphingomyelin phosphodiesterase 1; VCP/p97: valosin containing protein; WT: wild-type.

Sphingolipid and Endocannabinoid Profiles in Adult Attention Deficit Hyperactivity Disorder

Genes encoding endocannabinoid and sphingolipid metabolism pathways were suggested to contribute to the genetic risk towards attention deficit hyperactivity disorder (ADHD). The present pilot study assessed plasma concentrations of candidate endocannabinoids, sphingolipids and ceramides in individuals with adult ADHD in comparison with healthy controls and patients with affective disorders. Targeted lipid analyses of 23 different lipid species were performed in 71 mental disorder patients and 98 healthy controls (HC). The patients were diagnosed with adult ADHD (n = 12), affective disorder (major depression, MD n = 16 or bipolar disorder, BD n = 6) or adult ADHD with comorbid affective disorders (n = 37). Canonical discriminant analysis and CHAID analyses were used to identify major components that predicted the diagnostic group. ADHD patients had increased plasma concentrations of sphingosine-1-phosphate (S1P d18:1) and sphinganine-1-phosphate (S1P d18:0). In addition, the endocannabinoids, anandamide (AEA) and arachidonoylglycerol were increased. MD/BD patients had increased long chain ceramides, most prominently Cer22:0, but low endocannabinoids in contrast to ADHD patients. Patients with ADHD and comorbid affective disorders displayed increased S1P d18:1 and increased Cer22:0, but the individual lipid levels were lower than in the non-comorbid disorders. Sphingolipid profiles differ between patients suffering from ADHD and affective disorders, with overlapping patterns in comorbid patients. The S1P d18:1 to Cer22:0 ratio may constitute a diagnostic or prognostic tool.

Sapropterin (BH4) Aggravates Autoimmune Encephalomyelitis in Mice

Depletion of the enzyme cofactor, tetrahydrobiopterin (BH4), in T-cells was shown to prevent their proliferation upon receptor stimulation in models of allergic inflammation in mice, suggesting that BH4 drives autoimmunity. Hence, the clinically available BH4 drug (sapropterin) might increase the risk of autoimmune diseases. The present study assessed the implications for multiple sclerosis (MS) as an exemplary CNS autoimmune disease. Plasma levels of biopterin were persistently low in MS patients and tended to be lower with high Expanded Disability Status Scale (EDSS). Instead, the bypass product, neopterin, was increased. The deregulation suggested that BH4 replenishment might further drive the immune response or beneficially restore the BH4 balances. To answer this question, mice were treated with sapropterin in immunization-evoked autoimmune encephalomyelitis (EAE), a model of multiple sclerosis. Sapropterin-treated mice had higher EAE disease scores associated with higher numbers of T-cells infiltrating the spinal cord, but normal T-cell subpopulations in spleen and blood. Mechanistically, sapropterin treatment was associated with increased plasma levels of long-chain ceramides and low levels of the poly-unsaturated fatty acid, linolenic acid (FA18:3). These lipid changes are known to contribute to disruptions of the blood-brain barrier in EAE mice. Indeed, RNA data analyses revealed upregulations of genes involved in ceramide synthesis in brain endothelial cells of EAE mice (LASS6/CERS6, LASS3/CERS3, UGCG, ELOVL6, and ELOVL4). The results support the view that BH4 fortifies autoimmune CNS disease, mechanistically involving lipid deregulations that are known to contribute to the EAE pathology.

Brain lipidomics as a rising field in neurodegenerative contexts: Perspectives with Machine Learning approaches

Lipids are essential for cellular functioning considering their role in membrane composition, signaling, and energy metabolism. The brain is the second most abundant organ in terms of lipid concentration and diversity only after adipose tissue. However, in the central system (CNS) lipid dysregulation has been linked to the etiology, progression, and severity of neurodegenerative diseases such as Alzheimeŕs, Parkinson, and Multiple Sclerosis. Advances in the human genome and subsequent sequencing technologies allowed us the study of lipidomics as a promising approach to diagnosis and treatment of neurodegeneration. Lipidomics advances rapidly increased the amount and quality of data allowing the integration with other omic types as well as implementing novel bioinformatic and quantitative tools such as machine learning (ML). Integration of lipidomics data with ML, as a powerful quantitative predictive approach, led to improvements in diagnostic biomarker prediction, clinical data integration, network, and systems approaches for neural behavior, novel etiology markers for inflammation, and neurodegeneration progression and even Mass Spectrometry image analysis. In this sense, by exploiting lipidomics data with ML is possible to improve the identification of new biomarkers or unveil new molecular mechanisms associated with lipid impairment across neurodegeneration. In this review, we present the lipidomic neurobiology state-of-the-art highlighting its potential applications to study neurodegenerative conditions. Also, we present theoretical background, applications, and advances in the integration of lipidomics with ML. This review opens the door to new approaches in this rising field.

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

INTRODUCTION

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

OBJECTIVE

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

MATERIALS AND METHODS

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

CONCLUSIONS

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

Machine-learning-based knowledge discovery in rheumatoid arthritis-related registry data to identify predictors of persistent pain

Early detection of patients with chronic diseases at risk of developing persistent pain is clinically desirable for timely initiation of multimodal therapies. Quality follow-up registries may provide the necessary clinical data; however, their design is not focused on a specific research aim, which poses challenges on the data analysis strategy. Here, machine-learning was used to identify early parameters that provide information about a future development of persistent pain in rheumatoid arthritis (RA). Data of 288 patients were queried from a registry based on the Swedish Epidemiological Investigation of RA. Unsupervised data analyses identified the following 3 distinct patient subgroups: low-, median-, and high-persistent pain intensity. Next, supervised machine-learning, implemented as random forests followed by computed ABC analysis-based item categorization, was used to select predictive parameters among 21 different demographic, patient-rated, and objective clinical factors. The selected parameters were used to train machine-learned algorithms to assign patients pain-related subgroups (1000 random resamplings, 2/3 training, and 1/3 test data). Algorithms trained with 3-month data of the patient global assessment and health assessment questionnaire provided pain group assignment at a balanced accuracy of 70%. When restricting the predictors to objective clinical parameters of disease severity, swollen joint count and tender joint count acquired at 3 months provided a balanced accuracy of RA of 59%. Results indicate that machine-learning is suited to extract knowledge from data queried from pain- and disease-related registries. Early functional parameters of RA are informative for the development and degree of persistent pain.

Disrupted Lipid Metabolism in Multiple Sclerosis: A Role for Liver X Receptors?

Multiple sclerosis (MS) is a chronic neurological disease driven by autoimmune, inflammatory and neurodegenerative processes leading to neuronal demyelination and subsequent degeneration. Systemic lipid metabolism is disturbed in people with MS, and lipid metabolic pathways are crucial to the protective process of remyelination. The lipid-activated transcription factors liver X receptors (LXRs) are important integrators of lipid metabolism and immunity. Consequently, there is a strong interest in targeting these receptors in a number of metabolic and inflammatory diseases, including MS. We have reviewed the evidence for involvement of LXR-driven lipid metabolism in the dysfunction of peripheral and brain-resident immune cells in MS, focusing on human studies, both the relapsing remitting and progressive phases of the disease are discussed. Finally, we discuss the therapeutic potential of modulating the activity of these receptors with existing pharmacological agents and highlight important areas of future research.

Plasma lipidomics of monozygotic twins discordant for multiple sclerosis

Blood biomarkers of multiple sclerosis (MS) can provide a better understanding of pathophysiology and enable disease monitoring. Here, we performed quantitative shotgun lipidomics on the plasma of a unique cohort of 73 monozygotic twins discordant for MS. We analyzed 243 lipid species, evaluated lipid features such as fatty acyl chain length and number of acyl chain double bonds, and detected phospholipids that were significantly altered in the plasma of co‐twins with MS compared to their non‐affected siblings. Strikingly, changes were most prominent in ether phosphatidylethanolamines and ether phosphatidylcholines, suggesting a role for altered lipid signaling in the disease.

Blood pro-resolving mediators are linked with synovial pathology and are predictive of DMARD responsiveness in rheumatoid arthritis

Biomarkers are needed for predicting the effectiveness of disease modifying antirheumatic drugs (DMARDs). Here, using functional lipid mediator profiling and deeply phenotyped patients with early rheumatoid arthritis (RA), we observe that peripheral blood  specialized pro-resolving mediator (SPM) concentrations are linked with both DMARD responsiveness and disease pathotype. Machine learning analysis demonstrates that baseline plasma concentrations of resolvin D4, 10S, 17S-dihydroxy-docosapentaenoic acid, 15R-Lipoxin (LX)A4 and n-3 docosapentaenoic-derived Maresin 1 are predictive of DMARD responsiveness at 6 months. Assessment of circulating SPM concentrations 6-months after treatment initiation establishes that differences between responders and non-responders are maintained, with a decrease in SPM concentrations in patients resistant to DMARD therapy. These findings elucidate the potential utility of  plasma SPM concentrations as biomarkers of DMARD responsiveness in RA.

Lipidomic UPLC-MS/MS Profiles of Normal-Appearing White Matter Differentiate Primary and Secondary Progressive Multiple Sclerosis

Multiple sclerosis (MS) is a neurodegenerative inflammatory disease where an autoimmune response to components of the central nervous system leads to a loss of myelin and subsequent neurological deterioration. People with MS can develop primary or secondary progressive disease (PPMS, SPMS) and differentiation of the specific differences in the pathogenesis of these two courses, at the molecular level, is currently unclear. Recently, lipidomics studies using human biofluids, mainly plasma and cerebrospinal fluid, have highlighted a possible role for lipids in the initiation and progression of MS. However, there is a lack of lipidomics studies in MS on CNS tissues, such as normal-appearing white matter (NAWM), where local inflammation initially occurs. Herein, we developed an untargeted reverse phase ultra-performance liquid chromatography time of flight tandem mass spectrometry (RP-UPLC-TOF MS^E)-based workflow, in combination with multivariate and univariate statistical analysis, to assess significant differences in lipid profiles in brain NAWM from post-mortem cases of PPMS, SPMS and controls. Groups of eight control, nine PPMS and seven SPMS NAWM samples were used. Correlation analysis of the identified lipids by RP-UPLC-TOF MS^E was undertaken to remove those lipids that correlated with age, gender and post-mortem interval as confounding factors. We demonstrate that there is a significantly altered lipid profile of control cases compared with MS cases and that progressive disease, PPMS and SPMS, can be differentiated on the basis of the lipidome of NAWM with good sensitivity, specificity and prediction accuracy based on receiver operating characteristic (ROC) curve analysis. Metabolic pathway analysis revealed that the most altered lipid pathways between PPMS and SPMS were glycerophospholipid metabolism, glycerophosphatidyl inositol (GPI) anchor synthesis and linoleic acid metabolism. Further understanding of the impact of these lipid alterations described herein associated with progression will provide an increased understanding of the mechanisms underpinning progression and highlight possible new therapeutic targets.

Using Serum Metabolomics to Predict Development of Anti-drug Antibodies in Multiple Sclerosis Patients Treated With IFNβ

Background: Neutralizing anti-drug antibodies (ADA) can greatly reduce the efficacy of biopharmaceuticals used to treat patients with multiple sclerosis (MS). However, the biological factors pre-disposing an individual to develop ADA are poorly characterized. Thus, there is an unmet clinical need for biomarkers to predict the development of immunogenicity, and subsequent treatment failure. Up to 35% of MS patients treated with beta interferons (IFNβ) develop ADA. Here we use machine learning to predict immunogenicity against IFNβ utilizing serum metabolomics data. Methods: Serum samples were collected from 89 MS patients as part of the ABIRISK consortium-a multi-center prospective study of ADA development. Metabolites and ADA were quantified prior to and after IFNβ treatment. Thirty patients became ADA positive during the first year of treatment (ADA+). We tested the efficacy of six binary classification models using 10-fold cross validation; k-nearest neighbors, decision tree, random forest, support vector machine and lasso (Least Absolute Shrinkage and Selection Operator) logistic regression with and without interactions. Results: We were able to predict future immunogenicity from baseline metabolomics data. Lasso logistic regression with/without interactions and support vector machines were the most successful at identifying ADA+ or ADA- cases, respectively. Furthermore, patients who become ADA+ had a distinct metabolic response to IFNβ in the first 3 months, with 29 differentially regulated metabolites. Machine learning algorithms could also predict ADA status based on metabolite concentrations at 3 months. Lasso logistic regressions had the greatest proportion of correct classifications [F1 score (accuracy measure) = 0.808, specificity = 0.913]. Finally, we hypothesized that serum lipids could contribute to ADA development by altering immune-cell lipid rafts. This was supported by experimental evidence demonstrating that, prior to IFNβ exposure, lipid raft-associated lipids were differentially expressed between MS patients who became ADA+ or remained ADA-. Conclusion: Serum metabolites are a promising biomarker for prediction of ADA development in MS patients treated with IFNβ, and could provide novel insight into mechanisms of immunogenicity.

Lipid Mediator Profiles Predict Response to Therapy with an Oral Frankincense Extract in Relapsing-Remitting Multiple Sclerosis

Lipid mediators (LMs) are a unique class of immunoregulatory signalling molecules and known to be affected by frankincense extracts. We performed LM profiling by metabololipidomics in plasma samples from 28 relapsing-remitting multiple sclerosis (RR-MS) patients who took a standardised frankincense extract (SFE) daily for eight months in a clinical phase IIa trial (NCT01450124) and in 28 age- and gender-matched healthy controls. Magnetic resonance imaging, immunological outcomes and serum neurofilament light chain levels were correlated to changes in the LM profiles of the RR-MS cohort. Eight out of 44 analysed LMs were significantly reduced during an eight-month treatment period by the SFE and seven of these eight significant LM derive from the 5-lipoxygenase (5-LO) pathway. Baseline levels of 12- and 15-LO products were elevated in patients who exhibited disease activity (EDA) during SFE treatment compared to no-evidence-of-disease-activity (NEDA) patients and could predict treatment response to the SFE in a prediction model at baseline. Oral treatment with an SFE significantly reduces 5-LO-derived LMs in RR-MS patients during an eight-month treatment period. Treatment response to an SFE, however, seems to be related to 12-,15-LO and cyclooxygenase product levels before SFE exposure. Further studies should confirm their biomarker potential in RR-MS and SFE treatment.

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

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

Phase lag index and spectral power as QEEG features for identification of patients with mild cognitive impairment in Parkinson's disease

OBJECTIVES

To identify quantitative EEG frequency and connectivity features (Phase Lag Index) characteristic of mild cognitive impairment (MCI) in Parkinson's disease (PD) patients and to investigate if these features correlate with cognitive measures of the patients.

METHODS

We recorded EEG data for a group of PD patients with MCI (n = 27) and PD patients without cognitive impairment (n = 43) using a high-resolution recording system. The EEG files were processed and 66 frequency along with 330 connectivity (phase lag index, PLI) measures were calculated. These measures were used to classify MCI vs. MCI-free patients. We also assessed correlations of these features with cognitive tests based on comprehensive scores (domains).

RESULTS

PLI measures classified PD-MCI from non-MCI patients better than frequency measures. PLI in delta, theta band had highest importance for identifying patients with MCI. Amongst cognitive domains, we identified the most significant correlations between Memory and Theta PLI, Attention and Beta PLI.

CONCLUSION

PLI is an effective quantitative EEG measure to identify PD patients with MCI.

SIGNIFICANCE

We identified quantitative EEG measures which are important for early identification of cognitive decline in PD.

Alteration of Sphingolipids in Biofluids: Implications for Neurodegenerative Diseases

Sphingolipids (SL) modulate several cellular processes including cell death, proliferation and autophagy. The conversion of sphingomyelin (SM) to ceramide and the balance between ceramide and sphingosine-1-phosphate (S1P), also known as the SL rheostat, have been associated with oxidative stress and neurodegeneration. Research in the last decade has focused on the possibility of targeting the SL metabolism as a therapeutic option; and SL levels in biofluids, including serum, plasma, and cerebrospinal fluid (CSF), have been measured in several neurodegenerative diseases with the aim of finding a diagnostic or prognostic marker. Previous reviews focused on results from diseases such as Alzheimer's Disease (AD), evaluated total SL or species levels in human biofluids, post-mortem tissues and/or animal models. However, a comprehensive review of SL alterations comparing results from several neurodegenerative diseases is lacking. The present work compiles data from circulating sphingolipidomic studies and attempts to elucidate a possible connection between certain SL species and neurodegeneration processes. Furthermore, the effects of ceramide species according to their acyl-chain length in cellular pathways such as apoptosis and proliferation are discussed in order to understand the impact of the level alteration in specific species. Finally, enzymatic regulations and the possible influence of insulin resistance in the level alteration of SL are evaluated.

Targeted lipidomics reveal derangement of ceramides in major depression and bipolar disorder

Changes of sphingolipid metabolism were suggested to contribute to the patho-etiology of major depression (MD) and bipolar disorder (BD). In a pilot study we assessed if lipid allostasis manifested in pathological plasma concentrations of bioactive lipids i.e. endocannabinoids, sphingolipids, ceramides, and lysophosphatidic acids.

METHODS

Targeted and untargeted lipidomic analyses were performed according to GLP guidelines in 67 patients with unipolar or bipolar disorders (20-67 years, 36 male, 31 female) and 405 healthy controls (18-79 years, 142 m, 263 f), who were matched according to gender, age and body mass index. Multivariate analyses were used to identify major components, which accounted for the variance between groups and were able to predict group membership.

RESULTS

Differences between MD and BP patients versus controls mainly originated from ceramides and their hexosyl-metabolites (C16Cer, C18Cer, C20Cer, C22Cer, C24Cer and C24:1Cer; C24:1GluCer, C24LacCer), which were strongly increased, particularly in male patients. Ceramide levels were neither associated with the current episode, nor with the therapeutic improvement of the Montgomery Åsberg Depression Rating Scale (MARDS). However, long-chain ceramides were linearly associated with age, stronger in patients than controls, and with high plasma levels of diacyl- and triacylglycerols. Patients receiving antidepressants had higher ceramide levels than patients not taking these drugs. There was no such association with lithium or antipsychotics except for olanzapine.

CONCLUSION

Our data suggest that high plasma ceramides in patients with major depression and bipolar disorder are indicative of a high metabolic burden, likely aggravated by certain medications.

A computer-aided diagnosis of multiple sclerosis based on mfVEP recordings

Introduction

The aim of this study is to develop a computer-aided diagnosis system to identify subjects at differing stages of development of multiple sclerosis (MS) using multifocal visual-evoked potentials (mfVEPs). Using an automatic classifier, diagnosis is performed first on the eyes and then on the subjects.

Patients

MfVEP signals were obtained from patients with Radiologically Isolated Syndrome (RIS) (n = 30 eyes), patients with Clinically Isolated Syndrome (CIS) (n = 62 eyes), patients with definite MS (n = 56 eyes) and 22 control subjects (n = 44 eyes). The CIS and MS groups were divided into two subgroups: those with eyes affected by optic neuritis (ON) and those without (non-ON).

Methods

For individual eye diagnosis, a feature vector was formed with information about the intensity, latency and singular values of the mfVEP signals. A flat multiclass classifier (FMC) and a hierarchical classifier (HC) were tested and both were implemented using the k-Nearest Neighbour (k-NN) algorithm. The output of the best eye classifier was used to classify the subjects. In the event of divergence, the eye with the best mfVEP recording was selected.

Results

In the eye classifier, the HC performed better than the FMC (accuracy = 0.74 and extended Matthew Correlation Coefficient (MCC) = 0.68). In the subject classification, accuracy = 0.95 and MCC = 0.93, confirming that it may be a promising tool for MS diagnosis.

Conclusion

In addition to amplitude (axonal loss) and latency (demyelination), it has shown that the singular values of the mfVEP signals provide discriminatory information that may be used to identify subjects with differing degrees of the disease.

A Data Science-Based Analysis Points at Distinct Patterns of Lipid Mediator Plasma Concentrations in Patients With Dementia

Based on accumulating evidence of a role of lipid signaling in many physiological and pathophysiological processes including psychiatric diseases, the present data driven analysis was designed to gather information needed to develop a prospective biomarker, using a targeted lipidomics approach covering different lipid mediators. Using unsupervised methods of data structure detection, implemented as hierarchal clustering, emergent self-organizing maps of neuronal networks, and principal component analysis, a cluster structure was found in the input data space comprising plasma concentrations of d = 35 different lipid-markers of various classes acquired in n = 94 subjects with the clinical diagnoses depression, bipolar disorder, ADHD, dementia, or in healthy controls. The structure separated patients with dementia from the other clinical groups, indicating that dementia is associated with a distinct lipid mediator plasma concentrations pattern possibly providing a basis for a future biomarker. This hypothesis was subsequently assessed using supervised machine-learning methods, implemented as random forests or principal component analysis followed by computed ABC analysis used for feature selection, and as random forests, k-nearest neighbors, support vector machines, multilayer perceptron, and naïve Bayesian classifiers to estimate whether the selected lipid mediators provide sufficient information that the diagnosis of dementia can be established at a higher accuracy than by guessing. This succeeded using a set of d = 7 markers comprising GluCerC16:0, Cer24:0, Cer20:0, Cer16:0, Cer24:1, C16 sphinganine, and LacCerC16:0, at an accuracy of 77%. By contrast, using random lipid markers reduced the diagnostic accuracy to values of 65% or less, whereas training the algorithms with randomly permuted data was followed by complete failure to diagnose dementia, emphasizing that the selected lipid mediators were display a particular pattern in this disease possibly qualifying as biomarkers.