A symptom combination predicting treatment-resistant schizophrenia - A strategy for real-world clinical practice

Predicting treatment resistance in schizophrenia patients: Machine learning highlights the role of early pathophysiologic features

Detecting patients with a high-risk profile for treatment-resistant schizophrenia (TRS) can be beneficial for implementing individually adapted therapeutic strategies and better understanding the TRS etiology. The aim of this study was to explore, with machine learning methods, the impact of demographic and clinical patient characteristics on TRS prediction, for already established risk factors and unexplored ones. This was a retrospective study of 500 patients admitted during 2020 to the University Hospital Group for Paris Psychiatry. We hypothesized potential TRS risk factors. The selected features were coded into structured variables in a new dataset, by processing patients discharge summaries and medical narratives with natural-language processing methods. We compared three machine learning models (XGBoost, logistic elastic net regression, logistic regression without regularization) for predicting TRS outcome. We analysed feature impact on the models, suggesting the following factors as markers of a high-risk TRS profile: early age at first contact with psychiatry, antipsychotic treatment interruptions due to non-adherence, absence of positive symptoms at baseline, educational problems and adolescence mental disorders in the personal psychiatric history. Specifically, we found a significant association with TRS outcome for age at first contact with psychiatry and medication non-adherence. Our findings on TRS risk factors are consistent with the review of the literature and suggest potential in using early pathophysiologic features for TRS prediction. Results were encouraging with the use of natural-langage processing techniques to leverage raw data provided by discharge summaries, combined with machine leaning models. These findings are a promising step for helping clinicians adapt their guidelines to early detection of TRS.

A new schizophrenia screening instrument based on evaluating the patient's writing

Formal Thought Disorder (FTD) is a defining feature of schizophrenia, which is often assessed through patients' speech. Meanwhile, the written language is less studied. The aim of the present study is to establish and validate a comprehensive clinical screening scale, capturing the full variety of empirical characteristics of writing in patients with schizophrenia. The 16-item Screening Instrument for Schizophrenic Features in Writing (SISFiW) is derived from detailed literature review and a "brainstorming" discussion on 30 samples written by patients with schizophrenia. One hundred and fifty-seven participants (114 patients with an ICD-10 diagnoses of schizophrenia; 43 healthy control subjects) were interviewed and symptoms assessed with the Positive and Negative Syndrome Scale (PANSS) and the Scale for the Assessment of Thought, Language, and Communication (TLC). Article samples written by each participant were rated with the SISFiW. Results demonstrated significant difference of the SISFiW-total between the patient group and healthy controls [(3.61 ± 1.72) vs. (0.49 ± 0.63), t = 16.64, p<0.001]. The inter-rater reliability (weighted kappa = 0.72) and the internal consistency (Cronbach's alpha coefficient = 0.613) were acceptable, but correlations with the criterion (PANSS and TLC) were unremarkable. The ROC analysis indicated a cutoff point at 2 with the maximal sensitivity (93.0 %)/specificity (93.0 %). Discriminant analysis of the SISFiW items yielded 8 classifiers that discriminated between the diagnostic groups at a perfect overall performance (with 90.4 % of original and 88.5 % cross-validated grouped cases classified correctly). This instrument appears to be practicable and reliable, with relatively robust discriminatory power, and may serve as a complementary tool to existing FTD rating scales.

Using normative modeling to assess pharmacological treatment effect on brain state in patients with schizophrenia

Quantifying individual differences in neuroimaging metrics is attracting interest in clinical studies with mental disorders. Schizophrenia is diagnosed exclusively based on symptoms, and the biological heterogeneity makes it difficult to accurately assess pharmacological treatment effects on the brain state. Using the Cambridge Centre for Ageing and Neuroscience data set, we built normative models of brain states and mapped the deviations of the brain characteristics of each patient, to test whether deviations were related to symptoms, and further investigated the pharmacological treatment effect on deviation distributions. Specifically, we found that the patients can be divided into 2 groups: the normalized group had a normalization trend and milder symptoms at baseline, and the other group showed a more severe deviation trend. The baseline severity of the depression as well as the overall symptoms could predict the deviation of the static characteristics for the dorsal and ventral attention networks after treatment. In contrast, the positive symptoms could predict the deviations of the dynamic fluctuations for the default mode and dorsal attention networks after treatment. This work evaluates the effect of pharmacological treatment on static and dynamic brain states using an individualized approach, which may assist in understanding the heterogeneity of the illness pathology as well as the treatment response.

Genotypic and Haplotypic Association of Catechol-O-Methyltransferase rs4680 and rs4818 Gene Polymorphisms with Particular Clinical Symptoms in Schizophrenia

Catechol-O-methyl transferase (COMT) gene variants are involved in different neuropsychiatric disorders and cognitive impairments, associated with altered dopamine function. This study investigated the genotypic and haplotypic association of COMT rs4680 and rs4618 polymorphisms with the severity of cognitive and other clinical symptoms in 544 male and 385 female subjects with schizophrenia. COMT rs4818 G carriers were more frequent in male patients with mild abstract thinking difficulties, compared to CC homozygotes or C allele carriers. Male carriers of COMT rs4680 A allele had worse abstract thinking (N5) scores than GG carriers, whereas AA homozygotes were more frequent in male subjects with lower scores on the intensity of the somatic concern (G1) item, compared to G carriers. Male carriers of COMT rs4818-rs4680 GA haplotype had the highest scores on the G1 item (somatic concern), whereas GG haplotype carriers had the lowest scores on G2 (anxiety) and G6 (depression) items. COMT GG haplotype was less frequent in female patients with severe disturbance of volition (G13 item) compared to the group with mild symptoms, while CG haplotype was more frequent in female patients with severe then mild symptoms. These findings suggest the sex-specific genotypic and haplotypic association of COMT variants with a severity of cognitive and other clinical symptoms of schizophrenia.

Psychotic disorders as a framework for precision psychiatry

People with psychotic disorders can show marked interindividual variations in the onset of illness, responses to treatment and relapse, but they receive broadly similar clinical care. Precision psychiatry is an approach that aims to stratify people with a given disorder according to different clinical outcomes and tailor treatment to their individual needs. At present, interindividual differences in outcomes of psychotic disorders are difficult to predict on the basis of clinical assessment alone. Therefore, current research in psychosis seeks to build models that predict outcomes by integrating clinical information with a range of biological measures. Here, we review recent progress in the application of precision psychiatry to psychotic disorders and consider the challenges associated with implementing this approach in clinical practice.

Machine learning methods to predict outcomes of pharmacological treatment in psychosis

In recent years, machine learning (ML) has been a promising approach in the research of treatment outcome prediction in psychosis. In this study, we reviewed ML studies using different neuroimaging, neurophysiological, genetic, and clinical features to predict antipsychotic treatment outcomes in patients at different stages of schizophrenia. Literature available on PubMed until March 2022 was reviewed. Overall, 28 studies were included, among them 23 using a single-modality approach and 5 combining data from multiple modalities. The majority of included studies considered structural and functional neuroimaging biomarkers as predictive features used in ML models. Specifically, functional magnetic resonance imaging (fMRI) features contributed to antipsychotic treatment response prediction of psychosis with good accuracies. Additionally, several studies found that ML models based on clinical features might present adequate predictive ability. Importantly, by examining the additive effects of combining features, the predictive value might be improved by applying multimodal ML approaches. However, most of the included studies presented several limitations, such as small sample sizes and a lack of replication tests. Moreover, considerable clinical and analytical heterogeneity among included studies posed a challenge in synthesizing findings and generating robust overall conclusions. Despite the complexity and heterogeneity of methodology, prognostic features, clinical presentation, and treatment approaches, studies included in this review suggest that ML tools may have the potential to predict treatment outcomes of psychosis accurately. Future studies need to focus on refining feature characterization, validating prediction models, and evaluate their translation in real-world clinical practice.

Early Efficacy of Antipsychotic Medications at Week 2 Predicts Subsequent Responses at Week 6 in a Large-scale Randomized Controlled Trial

BACKGROUND

Since the early clinical efficacy of antipsychotics has not yet been well perceived, this study sought to decide whether the efficacy of antipsychotics at week 2 can predict subsequent responses at week 6 and identify how such predictive capacities vary among different antipsychotics and psychotic symptoms.

METHODS

A total of 3010 patients with schizophrenia enrolled in a randomized controlled trial (RCT) and received a 6-week treatment with one antipsychotic drug randomly chosen from five atypical antipsychotics (risperidone 2-6 mg/d, olanzapine 5-20 mg/d, quetiapine 400-750 mg/d, aripiprazole 10-30 mg/d, and ziprasidone 80-160 mg/d) and two typical antipsychotics (perphenazine 20-60 mg/d and haloperidol 6-20 mg/d). Early efficacy was defined as the reduction rate using the Positive and Negative Syndrome Scale (PANSS) total score at week 2. With cut-offs at 50% reduction, logistic regression, receiver operating characteristic (ROC) and random forests were adopted.

RESULTS

The reduction rate of PANSS total score and improvement of psychotic symptoms at week 2 enabled subsequent responses to 7 antipsychotics to be predicted, in which improvements in delusions, lack of judgment and insight, unusual thought content, and suspiciousness/ persecution were endowed with the greatest weight.

CONCLUSION

It is robust enough to clinically predict treatment responses to antipsychotics at week 6 using the reduction rate of PANSS total score and symptom relief at week 2. Psychiatric clinicians had better determine whether to switch the treatment plan by the first 2 weeks.

Disorganization domain as a putative predictor of Treatment Resistant Schizophrenia (TRS) diagnosis: A machine learning approach

BACKGROUND

Treatment Resistant Schizophrenia (TRS) is the persistence of significant symptoms despite adequate antipsychotic treatment. Although consensus guidelines are available, this condition remains often unrecognized and an average delay of 4-9 years in the initiation of clozapine, the gold standard for the pharmacological treatment of TRS, has been reported. We aimed to determine through a machine learning approach which domain of the Positive and Negative Syndrome Scale (PANSS) 5-factor model was most associated with TRS.

METHODS

In a cross-sectional design, 128 schizophrenia patients were classified as TRS (n = 58) or non-TRS (n = 60) after a structured retrospective-prospective analysis of treatment response. The random forest algorithm (RF) was trained to analyze the relationship between the presence/absence of TRS and PANSS-based psychopathological factor scores (positive, negative, disorganization, excitement, and emotional distress). As a complementary strategy to identify the variables most associated with the diagnosis of TRS, we included the variables selected by the RF algorithm in a multivariate logistic regression model.

RESULTS

according to the RF model, patients with higher disorganization, positive, and excitement symptom scores were more likely to be classified as TRS. The model showed an accuracy of 67.19%, a sensitivity of 62.07%, and a specificity of 71.43%, with an area under the curve (AUC) of 76.56%. The multivariate model including disorganization, positive, and excitement factors showed that disorganization was the only factor significantly associated with TRS. Therefore, the disorganization factor was the variable most consistently associated with the diagnosis of TRS in our sample.

A Guideline and Checklist for Initiating and Managing Clozapine Treatment in Patients with Treatment-Resistant Schizophrenia

Treatment-resistant schizophrenia (TRS) will affect about one in three patients with schizophrenia. Clozapine is the only treatment approved for TRS, and patients should be treated as soon as possible to improve their chances of achieving remission. Despite its effectiveness, concern over side effects, monitoring requirements, and inexperience with prescribing often result in long delays that can expose patients to unnecessary risks and compromise their chances of achieving favorable long-term outcomes. We critically reviewed the literature on clozapine use in TRS, focusing on guidelines, systematic reviews, and algorithms to identify strategies for improving clozapine safety and tolerability. Based on this, we have provided an overview of strategies to support early initiation of clozapine in patients with TRS based on the latest evidence and our clinical experience, and have summarized the key elements in a practical, evidence-based checklist for identifying and managing patients with TRS, with the aim of increasing confidence in prescribing and monitoring clozapine therapy.

Machine Learning Algorithm-Based Prediction Model for the Augmented Use of Clozapine with Electroconvulsive Therapy in Patients with Schizophrenia

The augmentation of clozapine with electroconvulsive therapy (ECT) has been an optimal treatment option for patients with treatment- or clozapine-resistant schizophrenia. Using data from the Research on Asian Psychotropic Prescription Patterns for Antipsychotics survey, which was the largest international psychiatry research collaboration in Asia, our study aimed to develop a machine learning algorithm-based substantial prediction model for the augmented use of clozapine with ECT in patients with schizophrenia in terms of precision medicine. A random forest model and least absolute shrinkage and selection operator (LASSO) model were used to develop a substantial prediction model for the augmented use of clozapine with ECT. Among the 3744 Asian patients with schizophrenia, those treated with a combination of clozapine and ECT were characterized by significantly greater proportions of females and inpatients, a longer duration of illness, and a greater prevalence of negative symptoms and social or occupational dysfunction than those not treated. In the random forest model, the area under the curve (AUC), which was the most preferred indicator of the prediction model, was 0.774. The overall accuracy was 0.817 (95% confidence interval, 0.793−0.839). Inpatient status was the most important variable in the substantial prediction model, followed by BMI, age, social or occupational dysfunction, persistent symptoms, illness duration > 20 years, and others. Furthermore, the AUC and overall accuracy of the LASSO model were 0.831 and 0.644 (95% CI, 0.615−0.672), respectively. Despite the subtle differences in both AUC and overall accuracy of the random forest model and LASSO model, the important variables were commonly shared by the two models. Using the machine learning algorithm, our findings allow the development of a substantial prediction model for the augmented use of clozapine with ECT in Asian patients with schizophrenia. This substantial prediction model can support further studies to develop a substantial prediction model for the augmented use of clozapine with ECT in patients with schizophrenia in a strict epidemiological context.

Network Analysis-Based Disentanglement of the Symptom Heterogeneity in Asian Patients with Schizophrenia: Findings from the Research on Asian Psychotropic Prescription Patterns for Antipsychotics

The symptom heterogeneity of schizophrenia is consistent with Wittgenstein's analogy of a language game. From the perspective of precision medicine, this study aimed to estimate the symptom presentation and identify the psychonectome in Asian patients, using data obtained from the Research on Asian Psychotropic Prescription Patterns for Antipsychotics. We constructed a network structure of the Brief Psychiatric Rating Scale (BPRS) items in 1438 Asian patients with schizophrenia. Furthermore, all the BPRS items were considered to be an ordered categorical variable ranging in value from 1-7. Motor retardation was situated most centrally within the BPRS network structure, followed by depressive mood and unusual thought content. Contrastingly, hallucinatory behavior was situated least centrally within the network structure. Using a community detection algorithm, the BPRS items were organized into positive, negative, and general symptom clusters. Overall, DSM symptoms were not more central than non-DSM symptoms within the symptom network of Asian patients with schizophrenia. Thus, motor retardation, which results from the unmet needs associated with current antipsychotic medications for schizophrenia, may be a tailored treatment target for Asian patients with schizophrenia. Based on these findings, targeting non-dopamine systems (glutamate, γ-aminobutyric acid) may represent an effective strategy with respect to precision medicine for psychosis.

Formal thought disorder in patients with first-episode schizophrenia: Results of a one-year follow-up study

Formal thought disorder (FTD) refers to abnormal speech patterns that can be characterized by deficiencies in thought organization and direction. The present study aimed to assess the factor structure of FTD and to examine its relationship with cognition and clinical features at first admission in patients with first-episode schizophrenia. We also examined the course of FTD during the twelve months after first admission. We assessed FTD using the alogia items of the Scale for the Assessment of Negative Symptoms and FTD items of the Scale for the Assessment of Positive Symptoms in 160 drug-naïve patients. A three-factor structure as a disorganization factor, poverty factor, and verbosity factor were found in principal component analysis. The poverty factor was correlated negatively with executive functions, attention, and global cognition. The poverty factor was also correlated with global functioning. Admission FTD factor scores were not related to global functioning and work/study status at one year. The positive-FTD score decreased from admission to the third month, but no change occurred from the third to the twelfth month. The negative-FTD score did not differ throughout the follow-up. Our findings showed that FTD had three factors. Each factor had a different relationship with cognition and functioning.

The Relationship between the Level of Anterior Cingulate Cortex Metabolites, Brain-Periphery Redox Imbalance, and the Clinical State of Patients with Schizophrenia and Personality Disorders

Schizophrenia is a complex mental disorder whose course varies with periods of deterioration and symptomatic improvement without diagnosis and treatment specific for the disease. So far, it has not been possible to clearly define what kinds of functional and structural changes are responsible for the onset or recurrence of acute psychotic decompensation in the course of schizophrenia, and to what extent personality disorders may precede the appearance of the appropriate symptoms. The work combines magnetic resonance spectroscopy imaging with clinical evaluation and laboratory tests to determine the likely pathway of schizophrenia development by identifying peripheral cerebral biomarkers compared to personality disorders. The relationship between the level of metabolites in the brain, the clinical status of patients according to International Statistical Classification of Diseases and Related Health Problems, 10th Revision ICD-10, duration of untreated psychosis (DUP), and biochemical indices related to redox balance (malondialdehyde), the efficiency of antioxidant systems (FRAP), and bioenergetic metabolism of mitochondria, were investigated. There was a reduction in the level of brain N-acetyl-aspartate and glutamate in the anterior cingulate gyrus of patients with schisophrenia compared to the other groups that seems more to reflect a biological etiopathological factor of psychosis. Decreased activity of brain metabolites correlated with increased peripheral oxidative stress (increased malondialdehyde MDA) associated with decreased efficiency of antioxidant systems (FRAP) and the breakdown of clinical symptoms in patients with schizophrenia in the course of psychotic decompensation compared to other groups. The period of untreated psychosis correlated negatively with glucose value in the brain of people with schizophrenia, and positively with choline level. The demonstrated differences between two psychiatric units, such as schizophrenia and personality disorders in relation to healthy people, may be used to improve the diagnosis and prognosis of schizophrenia compared to other heterogenous psychopathology in the future. The collapse of clinical symptoms of patients with schizophrenia in the course of psychotic decompensation may be associated with the occurrence of specific schizotypes, the determination of which is possible by determining common relationships between changes in metabolic activity of particular brain structures and peripheral parameters, which may be an important biological etiopathological factor of psychosis. Markers of peripheral redox imbalance associated with disturbed bioenergy metabolism in the brain may provide specific biological factors of psychosis however, they need to be confirmed in further studies.