Immune-based Machine learning prediction of diagnosis and illness state in schizophrenia and bipolar disorder.

BACKGROUND: Schizophrenia and bipolar disorder frequently face significant delay in diagnosis, leading to being missed or misdiagnosed in early stages. Both disorders have also been associated with trait and state immune abnormalities. Recent machine learning-based studies have shown encouraging results using diagnostic biomarkers in predictive models, but few have focused on immune-based markers. Our main objective was to develop supervised machine learning models to predict diagnosis and illness state in schizophrenia and bipolar disorder using only a panel of peripheral kynurenine metabolites and cytokines. METHODS: The cross-sectional I-GIVE cohort included hospitalized acute bipolar patients (n = 205), stable bipolar outpatients (n = 116), hospitalized acute schizophrenia patients (n = 111), stable schizophrenia outpatients (n = 75) and healthy controls (n = 185). Serum kynurenine metabolites, namely tryptophan (TRP), kynurenine (KYN), kynurenic acid (KA), quinaldic acid (QUINA), xanthurenic acid (XA), quinolinic acid (QUINO) and picolinic acid (PICO) were quantified using liquid chromatography-tandem mass spectrometry (LC-MS/MS), while V-plex Human Cytokine Assays were used to measure cytokines (interleukin-6 (IL-6), IL-8, IL-17, IL-12/IL23-P40, tumor necrosis factor-alpha (TNF-ɑ), interferon-gamma (IFN-γ)). Supervised machine learning models were performed using JMP Pro 17.0.0. We compared a primary analysis using nested cross-validation to a split set as sensitivity analysis. Post-hoc, we re-ran the models using only the significant features to obtain the key markers. RESULTS: The models yielded a good Area Under the Curve (AUC) (0.804, Positive Prediction Value (PPV) = 86.95; Negative Prediction Value (NPV) = 54.61) for distinguishing all patients from controls. This implies that a positive test is highly accurate in identifying the patients, but a negative test is inconclusive. Both schizophrenia patients and bipolar patients could each be separated from controls with a good accuracy (SCZ AUC 0.824; BD AUC 0.802). Overall, increased levels of IL-6, TNF-ɑ and PICO and decreased levels of IFN-γ and QUINO were predictive for an individual being classified as a patient. Classification of acute versus stable patients reached a fair AUC of 0.713. The differentiation between schizophrenia and bipolar disorder yielded a poor AUC of 0.627. CONCLUSIONS: This study highlights the potential of using immune-based measures to build predictive classification models in schizophrenia and bipolar disorder, with IL-6, TNF-ɑ, IFN-γ, QUINO and PICO as key candidates. While machine learning models successfully distinguished schizophrenia and bipolar disorder from controls, the challenges in differentiating schizophrenic from bipolar patients likely reflect shared immunological pathways by the both disorders and confounding by a larger state-specific effect. Larger multi-centric studies and multi-domain models are needed to enhance reliability and translation into clinic.

Kynurenine pathway abnormalities are state-specific but not diagnosis-specific in schizophrenia and bipolar disorder.

Schizophrenia (SCZ) and bipolar disorder (BD) are associated with immunological dysfunctions that have been hypothesized to lead to clinical symptomatology in particular through kynurenine pathway abnormalities. The aim of this study was thus to investigate the impact of serum kynurenine metabolite levels on diagnosis, clinical state, symptom severity and clinical course in a large French transdiagnostic cohort of SCZ and BD patients. Four patient groups (total n = 507) were included in a cross-sectional observational study: 1) hospitalized acute bipolar patients (n = 205); 2) stable bipolar outpatients (n = 116); 3) hospitalized acute schizophrenia patients (n = 111) and 4) stable schizophrenia outpatients (n = 75), in addition to healthy controls (HC) (n = 185). The quantitative determination of serum kynurenine metabolites was performed using liquid chromatography-tandem mass spectrometry. Kynurenine levels were lower in all patients combined compared to HC while ANCOVA analyses did not reveal inter-diagnostic difference between SCZ and BD. Interestingly, hospitalized patients of both diagnostic groups combined displayed significantly lower kynurenine levels than stabilized outpatients. Psychotic symptoms were associated with lower quinaldic acid (F = 9.18, p=<.001), which is KAT-driven, whereas a longer duration of illness contributed to abnormalities in tryptophan (F = 5.41, p = .023), kynurenine (F = 16.93, p=<.001), xanthurenic acid (F = 9.34, p = .002), quinolinic acid (F = 9.18, p = .003) and picolinic acid (F = 4.15, p = .043), metabolized through the KMO-branch. These data confirm illness state rather than diagnosis to drive KP alterations in SCZ and BD. Lower levels of KP metabolites can thus be viewed as a transdiagnostic feature of SCZ and BD, independently associated with acute symptomatology and a longer duration of illness. Quinaldic acid has seldomly been investigated by previous studies and appears an important state marker in SCZ and BD. As serum samples are used in this study, it is not possible to extrapolate these findings to the brain.

Brain Versus Blood: A Systematic Review on the Concordance Between Peripheral and Central Kynurenine Pathway Measures in Psychiatric Disorders.

Objective: Disturbances in the kynurenine pathway have been implicated in the pathophysiology of psychotic and mood disorders, as well as several other psychiatric illnesses. It remains uncertain however to what extent metabolite levels detectable in plasma or serum reflect brain kynurenine metabolism and other disease-specific pathophysiological changes. The primary objective of this systematic review was to investigate the concordance between peripheral and central (CSF or brain tissue) kynurenine metabolites. As secondary aims we describe their correlation with illness course, treatment response, and neuroanatomical abnormalities in psychiatric diseases. Methods: We performed a systematic literature search until February 2021 in PubMed. We included 27 original research articles describing a correlation between peripheral and central kynurenine metabolite measures in preclinical studies and human samples from patients suffering from neuropsychiatric disorders and other conditions. We also included 32 articles reporting associations between peripheral KP markers and symptom severity, CNS pathology or treatment response in schizophrenia, bipolar disorder or major depressive disorder. Results: For kynurenine and 3-hydroxykynurenine, moderate to strong concordance was found between peripheral and central concentrations not only in psychiatric disorders, but also in other (patho)physiological conditions. Despite discordant findings for other metabolites (mainly tryptophan and kynurenic acid), blood metabolite levels were associated with clinical symptoms and treatment response in psychiatric patients, as well as with observed neuroanatomical abnormalities and glial activity. Conclusion: Only kynurenine and 3-hydroxykynurenine demonstrated a consistent and reliable concordance between peripheral and central measures. Evidence from psychiatric studies on kynurenine pathway concordance is scarce, and more research is needed to determine the validity of peripheral kynurenine metabolite assessment as proxy markers for CNS processes. Peripheral kynurenine and 3-hydroxykynurenine may nonetheless represent valuable predictive and prognostic biomarker candidates for psychiatric disorders.

Tryptophan Catabolites in Bipolar Disorder: A Meta-Analysis.

Objective: Tryptophan catabolites (TRYCATs) are implicated in the pathophysiology of mood disorders by mediating immune-inflammation and neurodegenerative processes. We performed a meta-analysis of TRYCAT levels in bipolar disorder (BD) patients compared to healthy controls. Methods: A systematic literature search in seven electronic databases (PubMed, Embase, Web of Science, Cochrane, Emcare, PsycINFO, Academic Search Premier) was conducted on TRYCAT levels in cerebrospinal fluid or peripheral blood according to the PRISMA statement. A minimum of three studies per TRYCAT was required for inclusion. Standardized mean differences (SMD) were computed using random effect models. Subgroup analyses were performed for BD patients in a different mood state (depressed, manic). The methodological quality of the studies was rated using the modified Newcastle-Ottawa Quality assessment Scale. Results: Twenty-one eligible studies were identified. Peripheral levels of tryptophan (SMD = -0.44; p < 0.001), kynurenine (SMD = - 0.3; p = 0.001) and kynurenic acid (SMD = -.45; p = < 0.001) were lower in BD patients versus healthy controls. In the only three eligible studies investigating TRP in cerebrospinal fluid, tryptophan was not significantly different between BD and healthy controls. The methodological quality of the studies was moderate. Subgroup analyses revealed no significant difference in TRP and KYN values between manic and depressed BD patients, but these results were based on a limited number of studies. Conclusion: The TRYCAT pathway appears to be downregulated in BD patients. There is a need for more and high-quality studies of peripheral and central TRYCAT levels, preferably using longitudinal designs.