Multi-dimensional predictions of psychotic symptoms via machine learning

Accuracy of machine learning methods in predicting prognosis of patients with psychotic spectrum disorders: a systematic review

OBJECTIVES

We aimed to examine the predictive accuracy of functioning, relapse or remission among patients with psychotic disorders, using machine learning methods. We also identified specific features that were associated with these clinical outcomes.

DESIGN

The methodology of this review was guided by the Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy.

DATA SOURCES

CINAHL, EMBASE, PubMed, PsycINFO, Scopus and ScienceDirect were searched for relevant articles from database inception until 21 November 2024.

ELIGIBILITY CRITERIA

Studies were included if they involved the use of machine learning methods to predict functioning, relapse and/or remission among individuals with psychotic spectrum disorders.

DATA EXTRACTION AND SYNTHESIS

Two independent reviewers screened the records from the database search. Risk of bias was evaluated using the Quality Assessment of Diagnostic Accuracy Studies tool from Cochrane. Synthesised findings were presented in tables.

RESULTS

23 studies were included in the review, which were mostly conducted in the west (91%). Predictive summary area under the curve values for functioning, relapse and remission were 0.63-0.92 (poor to outstanding), 0.45-0.95 (poor to outstanding), 0.70-0.79 (acceptable), respectively. Logistic regression and random forest were the best performing algorithms. Factors influencing outcomes included demographic (age, ethnicity), illness (duration of untreated illness, types of symptoms), functioning (baseline functioning, interpersonal relationships and activity engagement), treatment variables (use of higher doses of antipsychotics, electroconvulsive therapy), data from passive sensor (call log, distance travelled, time spent in certain locations) and online activities (time of use, use of certain words, changes in search frequencies and length of queries).

CONCLUSION

Machine learning methods show promise in the prediction of prognosis (specifically functioning, relapse and remission) of mental disorders based on relevant collected variables. Future machine learning studies may want to focus on the inclusion of a broader swathe of variables including ecological momentary assessments, with a greater amount of good quality big data covering longer longitudinal illness courses and coupled with external validation of study findings.

PROSPERO REGISTRATION NUMBER

The review was registered on PROSPERO, ID: CRD42023441108.

Improved patient identification by incorporating symptom severity in deep learning using neuroanatomic images in first episode schizophrenia

Brain alterations associated with illness severity in schizophrenia remain poorly understood. Establishing linkages between imaging biomarkers and symptom expression may enhance mechanistic understanding of acute psychotic illness. Constructing models using MRI and clinical features together to maximize model validity may be particularly useful for these purposes. A multi-task deep learning model for standard case/control recognition incorporated with psychosis symptom severity regression was constructed with anatomic MRI collected from 286 patients with drug-naïve first-episode schizophrenia and 330 healthy controls from two datasets, and validated with an independent dataset including 40 first-episode schizophrenia. To evaluate the contribution of regression to the case/control recognition, a single-task classification model was constructed. Performance of unprocessed anatomical images and of predefined imaging features obtained using voxel-based morphometry (VBM) and surface-based morphometry (SBM), were examined and compared. Brain regions contributing to the symptom severity regression and illness identification were identified. Models developed with unprocessed images achieved greater group separation than either VBM or SBM measurements, differentiating schizophrenia patients from healthy controls with a balanced accuracy of 83.0% with sensitivity = 76.1% and specificity = 89.0%. The multi-task model also showed superior performance to single-task classification model without considering clinical symptoms. These findings showed high replication in the site-split validation and external validation analyses. Measurements in parietal, occipital and medial frontal cortex and bilateral cerebellum had the greatest contribution to the multi-task model. Incorporating illness severity regression in pattern recognition algorithms, our study developed an MRI-based model that was of high diagnostic value in acutely ill schizophrenia patients, highlighting clinical relevance of the model.

RDoC Framework Through the Lens of Predictive Processing: Focusing on Cognitive Systems Domain

In response to shortcomings of the current classification system in translating discoveries from basic science to clinical applications, NIMH offers a new framework for studying mental health disorders called Research Domain Criteria (RDoC). This framework holds a multidimensional outlook on psychopathologies focusing on functional domains of behavior and their implementing neural circuits. In parallel, the Predictive Processing (PP) framework stands as a leading theory of human brain function, offering a unified explanation for various types of information processing in the brain. While both frameworks share an interest in studying psychopathologies based on pathophysiology, their integration still needs to be explored. Here, we argued in favor of the explanatory power of PP to be a groundwork for the RDoC matrix in validating its constructs and creating testable hypotheses about mechanistic interactions between molecular biomarkers and clinical traits. Together, predictive processing may serve as a foundation for achieving the goals of the RDoC framework.

Multivariable prediction of functional outcome after first-episode psychosis: a crossover validation approach in EUFEST and PSYSCAN

Several multivariate prognostic models have been published to predict outcomes in patients with first episode psychosis (FEP), but it remains unclear whether those predictions generalize to independent populations. Using a subset of demographic and clinical baseline predictors, we aimed to develop and externally validate different models predicting functional outcome after a FEP in the context of a schizophrenia-spectrum disorder (FES), based on a previously published cross-validation and machine learning pipeline. A crossover validation approach was adopted in two large, international cohorts (EUFEST, n = 338, and the PSYSCAN FES cohort, n = 226). Scores on the Global Assessment of Functioning scale (GAF) at 12 month follow-up were dichotomized to differentiate between poor (GAF current < 65) and good outcome (GAF current ≥ 65). Pooled non-linear support vector machine (SVM) classifiers trained on the separate cohorts identified patients with a poor outcome with cross-validated balanced accuracies (BAC) of 65-66%, but BAC dropped substantially when the models were applied to patients from a different FES cohort (BAC = 50-56%). A leave-site-out analysis on the merged sample yielded better performance (BAC = 72%), highlighting the effect of combining data from different study designs to overcome calibration issues and improve model transportability. In conclusion, our results indicate that validation of prediction models in an independent sample is essential in assessing the true value of the model. Future external validation studies, as well as attempts to harmonize data collection across studies, are recommended.

Early and late contingent negative variation (CNV) reflect different aspects of deficits in schizophrenia

Abnormal reward processing and psychomotor slowing are well-known in schizophrenia (SZ). As a slow frontocentral potential, contingent negative variation (CNV) is associated with anticipatory attention, motivation and motor planning. The present study aims to evaluate the early and late amplitude and latencies of CNV in patients with SZ compared to healthy controls during a reward processing task and to show its association with clinical symptoms. We recruited 21 patients with SZ and 22 healthy controls to compare early and late CNV amplitude and latency values during a Monetary Incentive Delay (MID) Task between groups. Patients' symptom severity, levels of negative symptoms and depressive symptoms were assessed. Clinical features of the patients were further examined for their relation with CNV components. In conclusion, we found decreased early CNV amplitudes in SZ during the reward condition. They also displayed diminished and shortened late CNV responses for incentive cues, specifically at the central location. Furthermore, early CNV amplitudes exhibited a significant correlation with positive symptoms. Both CNV latencies were linked with medication dosage and the behavioural outcomes of the MID task. We revealed that early and late CNV exhibit different functions in neurophysiology and correspond to various facets of the deficits observed in patients. Our findings also emphasized that slow cortical potentials are indicative of deficient motivational processes as well as impaired reaction preparation in SZ. To gain a deeper understanding of the cognitive and motor impairments associated with psychosis, future studies must compare the effects of CNV in the early and late phases.

Using support vector machine to explore the difference of function connection between deficit and non-deficit schizophrenia based on gray matter volume

Objective

Schizophrenia can be divided into deficient schizophrenia (DS) and non-deficient schizophrenia (NDS) according to the presence of primary and persistent negative symptoms. So far, there are few studies that have explored the differences in functional connectivity (FC) between the different subtypes based on the region of interest (ROI) from GMV (Gray matter volume), especially since the characteristics of brain networks are still unknown. This study aimed to investigate the alterations of functional connectivity between DS and NDS based on the ROI obtained by machine learning algorithms and differential GMV. Then, the relationships between the alterations and the clinical symptoms were analyzed. In addition, the thalamic functional connection imbalance in the two groups was further explored.

Methods

A total of 16 DS, 31 NDS, and 38 health controls (HC) underwent resting-state fMRI scans, patient group will further be evaluated by clinical scales including the Brief Psychiatric Rating Scale (BPRS), the Scale for the Assessment of Negative Symptoms (SANS), and the Scale for the Assessment of Positive Symptoms (SAPS). Based on GMV image data, a support vector machine (SVM) is used to classify DS and NDS. Brain regions with high weight in the classification were used as seed points in whole-brain FC analysis and thalamic FC imbalance analysis. Finally, partial correlation analysis explored the relationships between altered FC and clinical scale in the two subtypes.

Results

The relatively high classification accuracy is obtained based on the SVM. Compared to HC, the FC increased between the right inferior parietal lobule (IPL.R) bilateral thalamus, and lingual gyrus, and between the right inferior temporal gyrus (ITG.R) and the Salience Network (SN) in NDS. The FC between the right thalamus (THA.R) and Visual network (VN), between ITG.R and right superior occipital gyrus in the DS group was higher than that in HC. Furthermore, compared with NDS, the FC between the ITG.R and the left superior and middle frontal gyrus decreased in the DS group. The thalamic FC imbalance, which is characterized by frontotemporal-THA.R hypoconnectivity and sensory motor network (SMN)-THA.R hyperconnectivity was found in both subtypes. The FC value of THA.R and SMN was negatively correlated with the SANS score in the DS group but positively correlated with the SAPS score in the NDS group.

Conclusion

Using an SVM classification method and based on an ROI from GMV, we highlighted the difference in functional connectivity between DS and NDS from the local to the brain network, which provides new information for exploring the neural physiopathology of the two subtypes of schizophrenic.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Computational Modeling of Electroencephalography and Functional Magnetic Resonance Imaging Paradigms Indicates a Consistent Loss of Pyramidal Cell Synaptic Gain in Schizophrenia

BACKGROUND

Diminished synaptic gain-the sensitivity of postsynaptic responses to neural inputs-may be a fundamental synaptic pathology in schizophrenia. Evidence for this is indirect, however. Furthermore, it is unclear whether pyramidal cells or interneurons (or both) are affected, or how these deficits relate to symptoms.

METHODS

People with schizophrenia diagnoses (PScz) (n = 108), their relatives (n = 57), and control subjects (n = 107) underwent 3 electroencephalography (EEG) paradigms-resting, mismatch negativity, and 40-Hz auditory steady-state response-and resting functional magnetic resonance imaging. Dynamic causal modeling was used to quantify synaptic connectivity in cortical microcircuits.

RESULTS

Classic group differences in EEG features between PScz and control subjects were replicated, including increased theta and other spectral changes (resting EEG), reduced mismatch negativity, and reduced 40-Hz power. Across all 4 paradigms, characteristic PScz data features were all best explained by models with greater self-inhibition (decreased synaptic gain) in pyramidal cells. Furthermore, disinhibition in auditory areas predicted abnormal auditory perception (and positive symptoms) in PScz in 3 paradigms.

CONCLUSIONS

First, characteristic EEG changes in PScz in 3 classic paradigms are all attributable to the same underlying parameter change: greater self-inhibition in pyramidal cells. Second, psychotic symptoms in PScz relate to disinhibition in neural circuits. These findings are more commensurate with the hypothesis that in PScz, a primary loss of synaptic gain on pyramidal cells is then compensated by interneuron downregulation (rather than the converse). They further suggest that psychotic symptoms relate to this secondary downregulation.

Predicting subclinical psychotic-like experiences on a continuum using machine learning

Previous studies applying machine learning methods to psychosis have primarily been concerned with the binary classification of chronic schizophrenia patients and healthy controls. The aim of this study was to use electroencephalographic (EEG) data and pattern recognition to predict subclinical psychotic-like experiences on a continuum between these two extremes in otherwise healthy people. We applied two different approaches to an auditory oddball regularity learning task obtained from N = 73 participants: A feature extraction and selection routine incorporating behavioural measures, event-related potential components and effective connectivity parameters; Regularisation of spatiotemporal maps of event-related potentials. Using the latter approach, optimal performance was achieved using the response to frequent, predictable sounds. Features within the P50 and P200 time windows had the greatest contribution toward lower Prodromal Questionnaire (PQ) scores and the N100 time window contributed most to higher PQ scores. As a proof-of-concept, these findings demonstrate that EEG data alone are predictive of individual psychotic-like experiences in healthy people. Our findings are in keeping with the mounting evidence for altered sensory responses in schizophrenia, as well as the notion that psychosis may exist on a continuum expanding into the non-clinical population.

Multi-dimensional predictions of psychotic symptoms via machine learning

The diagnostic criteria for schizophrenia comprise a diverse range of heterogeneous symptoms. As a result, individuals each present a distinct set of symptoms despite having the same overall diagnosis. Whilst previous machine learning studies have primarily focused on dichotomous patient-control classification, we predict the severity of each individual symptom on a continuum. We applied machine learning regression within a multi-modal fusion framework to fMRI and behavioural data acquired during an auditory oddball task in 80 schizophrenia patients. Brain activity was highly predictive of some, but not all symptoms, namely hallucinations, avolition, anhedonia and attention. Critically, each of these symptoms was associated with specific functional alterations across different brain regions. We also found that modelling symptoms as an ensemble of subscales was more accurate, specific and informative than models which predict compound scores directly. In principle, this approach is transferrable to any psychiatric condition or multi-dimensional diagnosis.