A computational algorithm for personalized medicine in schizophrenia

Precision Medicine Approaches to Mental Health Care

Developing a more comprehensive understanding of the physiological underpinnings of mental illness, precision medicine has the potential to revolutionize psychiatric care. With recent breakthroughs in next-generation multi-omics technologies and data analytics, it is becoming more feasible to leverage multimodal biomarkers, from genetic variants to neuroimaging biomarkers, to objectify diagnostics and treatment decisions in psychiatry and improve patient outcomes. Ongoing work in precision psychiatry will parallel progress in precision oncology and cardiology to develop an expanded suite of blood- and neuroimaging-based diagnostic tests, empower monitoring of treatment efficacy over time, and reduce patient exposure to ineffective treatments. The emerging model of precision psychiatry has the potential to mitigate some of psychiatry's most pressing issues, including improving disease classification, lengthy treatment duration, and suboptimal treatment outcomes. This narrative-style review summarizes some of the emerging breakthroughs and recurring challenges in the application of precision medicine approaches to mental health care.

Machine Learning and Pharmacogenomics at the Time of Precision Psychiatry

Traditional medicine and biomedical sciences are reaching a turning point because of the constantly growing impact and volume of Big Data. Machine Learning (ML) techniques and related algorithms play a central role as diagnostic, prognostic, and decision-making tools in this field. Another promising area becoming part of everyday clinical practice is personalized therapy and pharmacogenomics. Applying ML to pharmacogenomics opens new frontiers to tailored therapeutical strategies to help clinicians choose drugs with the best response and fewer side effects, operating with genetic information and combining it with the clinical profile. This systematic review aims to draw up the state-of-the-art ML applied to pharmacogenomics in psychiatry. Our research yielded fourteen papers; most were published in the last three years. The sample comprises 9,180 patients diagnosed with mood disorders, psychoses, or autism spectrum disorders. Prediction of drug response and prediction of side effects are the most frequently considered domains with the supervised ML technique, which first requires training and then testing. The random forest is the most used algorithm; it comprises several decision trees, reduces the training set's overfitting, and makes precise predictions. ML proved effective and reliable, especially when genetic and biodemographic information were integrated into the algorithm. Even though ML and pharmacogenomics are not part of everyday clinical practice yet, they will gain a unique role in the next future in improving personalized treatments in psychiatry.

Comparison of prediction methods for treatment continuation of antipsychotics in children and adolescents with schizophrenia

OBJECTIVE

There is little evidence for finding optimal antipsychotic treatment for schizophrenia, especially in paediatrics. To evaluate the performance and clinical benefit of several prediction methods for 1-year treatment continuation of antipsychotics.

DESIGN AND SETTINGS

Population-based prognostic study conducting using the nationwide claims database in Korea.

PARTICIPANTS

5109 patients aged 2-18 years who initiated antipsychotic treatment with risperidone/aripiprazole for schizophrenia between 2010 and 2017 were identified.

MAIN OUTCOME MEASURES

We used the conventional logistic regression (LR) and common six machine-learning methods (least absolute shrinkage and selection operator, ridge, elstic net, randomforest, gradient boosting machine, and superlearner) to derive predictive models for treatment continuation of antipsychotics. The performance of models was assessed using the Brier score (BS), area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). The clinical benefit of applying these models was also evaluated by comparing the treatment continuation rate between patients who received the recommended medication by models and patients who did not.

RESULTS

The gradient boosting machine showed the best performance in predicting treatment continuation for risperidone (BS, 0.121; AUROC, 0.686; AUPRC, 0.269). Among aripiprazole models, GBM for BS (0.114), SuperLearner for AUROC (0.688) and random forest for AUPRC (0.317) showed the best performance. Although LR showed lower performance than machine learnings, the difference was negligible. Patients who received recommended medication by these models showed a 1.2-1.5 times higher treatment continuation rate than those who did not.

CONCLUSIONS

All prediction models showed similar performance in predicting the treatment continuation of antipsychotics. Application of prediction models might be helpful for evidence-based decision-making in antipsychotic treatment.

Innovations in Genomics and Big Data Analytics for Personalized Medicine and Health Care: A Review

Big data in health care is a fast-growing field and a new paradigm that is transforming case-based studies to large-scale, data-driven research. As big data is dependent on the advancement of new data standards, technology, and relevant research, the future development of big data applications holds foreseeable promise in the modern day health care revolution. Enormously large, rapidly growing collections of biomedical omics-data (genomics, proteomics, transcriptomics, metabolomics, glycomics, etc.) and clinical data create major challenges and opportunities for their analysis and interpretation and open new computational gateways to address these issues. The design of new robust algorithms that are most suitable to properly analyze this big data by taking into account individual variability in genes has enabled the creation of precision (personalized) medicine. We reviewed and highlighted the significance of big data analytics for personalized medicine and health care by focusing mostly on machine learning perspectives on personalized medicine, genomic data models with respect to personalized medicine, the application of data mining algorithms for personalized medicine as well as the challenges we are facing right now in big data analytics.

Multivariate alterations in insula - Medial prefrontal cortex linked to genetics in 12q24 in schizophrenia

The direct effect of genetic variations on clinical phenotypes within schizophrenia (SZ) remains elusive. We examined the previously identified association of reduced gray matter concentration in the insula - medial prefrontal cortex and a quantitative trait locus located in 12q24 in a SZ dataset. The main analysis was performed on 1461 SNPs and 830 participants. The highest contributing SNPs were localized in five genes including TMEM119, which encodes a microglial marker, that is associated with neuroinflammation and Alzheimer's disease. The gene set in 12q4 may partially explain brain alterations in SZ, but they may also relate to other psychiatric and developmental disorders.

Review: Influence of the CYP450 Genetic Variation on the Treatment of Psychotic Disorders

Second-generation antipsychotic metabolism is mainly carried out by the CYP450 superfamily, which is highly polymorphic. Therefore, knowing the influence of the different known CYP450 polymorphisms on antipsychotic plasmatic levels and, consequently, the biological effect could contribute to a deeper knowledge of interindividual antipsychotic treatment variability, prompting possible solutions. Considering this, this state of the art review aimed to summarize the current knowledge about the influence of the diverse characterized phenotypes on the metabolism of the most used second-generation antipsychotics. Forty studies describing different single nucleotide polymorphisms (SNPs) associated with the genes CYP1A2, CYP2D6, CYP3A4, CYP3A5, and ABCB1 and their influence on pharmacokinetics of olanzapine, clozapine, aripiprazole, risperidone, and quetiapine. Most of the authors concluded that although significant differences in the pharmacokinetic parameters between the different phenotypes could be observed, more thorough studies describing pharmacokinetic interactions and environmental conditions, among other variables, are needed to fully comprehend these pharmacogenetic interactions.

Individual deviations from normative models of brain structure in a large cross-sectional schizophrenia cohort

The heterogeneity of schizophrenia has defied efforts to derive reproducible and definitive anatomical maps of structural brain changes associated with the disorder. We aimed to map deviations from normative ranges of brain structure for individual patients and evaluate whether the loci of individual deviations recapitulated group-average brain maps of schizophrenia pathology. For each of 48 white matter tracts and 68 cortical regions, normative percentiles of variation in fractional anisotropy (FA) and cortical thickness (CT) were established using diffusion-weighted and structural MRI from healthy adults (n = 195). Individuals with schizophrenia (n = 322) were classified as either within the normative range for healthy individuals of the same age and sex (5-95% percentiles), infra-normal (<5% percentile) or supra-normal (>95% percentile). Repeating this classification for each tract and region yielded a deviation map for each individual. Compared to the healthy comparison group, the schizophrenia group showed widespread reductions in FA and CT, involving virtually all white matter tracts and cortical regions. Paradoxically, however, no more than 15-20% of patients deviated from the normative range for any single tract or region. Furthermore, 79% of patients showed infra-normal deviations for at least one locus (healthy individuals: 59 ± 2%, p < 0.001). Thus, while infra-normal deviations were common among patients, their anatomical loci were highly inconsistent between individuals. Higher polygenic risk for schizophrenia associated with a greater number of regions with infra-normal deviations in CT (r = -0.17, p = 0.006). We conclude that anatomical loci of schizophrenia-related changes are highly heterogeneous across individuals to the extent that group-consensus pathological maps are not representative of most individual patients. Normative modeling can aid in parsing schizophrenia heterogeneity and guiding personalized interventions.

Application of a Pharmacogenetics-Based Precision Medicine Model (5SPM) to Psychotic Patients That Presented Poor Response to Neuroleptic Therapy

Antipsychotics are the keystone of the treatment of severe and prolonged mental disorders. However, there are many risks associated with these drugs and not all patients undergo full therapeutic profit from them. The application of the 5 Step Precision Medicine model(5SPM), based on the analysis of the pharmacogenetic profile of each patient, could be a helpful tool to solve many of the problematics traditionally associated with the neuroleptic treatment. In order to solve this question, a cohort of psychotic patients that showed poor clinical evolution was analyzed. After evaluating the relationship between the prescribed treatment and pharmacogenetic profile of each patient, a great number of pharmacological interactions and pharmacogenetical conflicts were found. After reconsidering the treatment of the conflictive cases, patients showed a substantial reduction on mean daily doses and polytherapy cases, which may cause less risk of adverse effects, greater adherence, and a reduction on economic costs.

Pharmacogenetics of antipsychotics: Clinical utility and implementation

Decades of research have produced extensive evidence of the contribution of genetic factors to the efficacy and toxicity of antipsychotics. Numerous genetic variants in genes controlling drug availability or involved in antipsychotic processes have been linked to treatment variability. The complex mechanism of action and multitarget profile of most antipsychotic drugs hinder the identification of pharmacogenetic markers of clinical value. Nevertheless, the validity of associations between variants in CYP1A2, CYP2D6, CYP2C19, ABCB1, DRD2, DRD3, HTR2A, HTR2C, BDNF, COMT, MC4R genes and antipsychotic response has been confirmed in independent candidate gene studies. Genome wide pharmacogenomic studies have proven the role of the glutamatergic pathway in mediating antipsychotic activity and have reported novel associations with antipsychotic response. However, only a limited number of the findings, mainly functional variants of CYP metabolic enzymes, have been shown to be of clinical utility and translated into useful pharmacogenetic markers. Based on the currently available information, actionable pharmacogenetics should be reduced to antipsychotics' dose adjustment according to the genetically predicted metabolic status (CYPs' profile) of the patient. Growing evidence suggests that such interventions will reduce antipsychotics' side-effects and increase treatment safety. Despite this evidence, the use of pharmacogenetics in psychiatric wards is minimal. Hopefully, further evidence on the clinical and economic benefits, the development of clinical protocols based on pharmacogenetic information, and improved and cheaper genetic testing will increase the implementation of pharmacogenetic guided prescription in clinical settings.

Four Actionable Bottlenecks and Potential Solutions to Translating Psychiatric Genetics Research: An Expert Review

BACKGROUND

Psychiatric genetics has had limited success in translational efforts. A thorough understanding of the present state of translation in this field will be useful in the facilitation and assessment of future translational progress.

PURPOSE

A narrative literature review was conducted. Combinations of 3 groups of terms were searched in EBSCOhost, Google Scholar, and PubMed. The review occurred in multiple steps, including abstract collection, inclusion/exclusion criteria review, coding, and analysis of included papers.

RESULTS

One hundred and fourteen articles were analyzed for the narrative review. Across those, 4 bottlenecks were noted that, if addressed, may provide insights and help improve and increase translation in the field of psychiatric genetics. These 4 bottlenecks are emphasizing linear translational frameworks, relying on molecular genomic findings, prioritizing certain psychiatric disorders, and publishing more reviews than experiments.

CONCLUSIONS

These entwined bottlenecks are examined with one another. Awareness of these bottlenecks can inform stakeholders who work to translate and/or utilize psychiatric genetic information. Potential solutions include utilizing nonlinear translational frameworks as well as a wider array of psychiatric genetic information (e.g., family history and gene-environment interplay) in this area of research, expanding which psychiatric disorders are considered for translation, and when possible, conducting original research. Researchers are urged to consider how their research is translational in the context of the frameworks, genetic information, and psychiatric disorders discussed in this review. At a broader level, these efforts should be supported with translational efforts in funding and policy shifts.

Personalized medicine begins with the phenotype: identifying antipsychotic response phenotypes in a first-episode psychosis cohort

AIMS

Here, we present a clustering strategy to identify phenotypes of antipsychotic (AP) response by using longitudinal data from patients presenting first-episode psychosis (FEP).

METHOD

One hundred and ninety FEP with complete data were selected from the PEPs project. The efficacy was assessed using total PANSS, and adverse effects using total UKU, during one-year follow-up. We used the Klm3D method to cluster longitudinal data.

RESULTS

We identified four clusters: cluster A, drug not toxic and beneficial; cluster B, drug beneficial but toxic; cluster C, drug neither toxic nor beneficial; and cluster D, drug toxic and not beneficial. These groups significantly differ in baseline demographics, clinical, and neuropsychological characteristics (PAS, total PANSS, DUP, insight, pIQ, age of onset, cocaine use and family history of mental illness).

CONCLUSIONS

The results presented here allow the identification of phenotypes of AP response that differ in well-known simple and classic clinical variables opening the door to clinical prediction and application of personalized medicine.

Development and Validation of a Machine Learning Individualized Treatment Rule in First-Episode Schizophrenia

IMPORTANCE

Little guidance exists to date on how to select antipsychotic medications for patients with first-episode schizophrenia.

OBJECTIVE

To develop a preliminary individualized treatment rule (ITR) for patients with first-episode schizophrenia.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study obtained data from Taiwan's National Health Insurance Research Database on patients with prescribed antipsychotic medications, ambulatory claims, or discharge diagnoses of a schizophrenic disorder between January 1, 2005, and December 31, 2011. An ITR was developed by applying a targeted minimum loss-based ensemble machine learning method to predict treatment success from baseline clinical and demographic data in a 70% training sample. The model was validated in the remaining 30% of the sample. The probability of treatment success was estimated for each medication for each patient under the model. The analysis was conducted between July 16, 2018, and July 15, 2019.

EXPOSURES

Fifteen different antipsychotic medications.

MAIN OUTCOMES AND MEASURES

Treatment success was defined as not switching medication and not being hospitalized for 12 months.

RESULTS

Among the 32 277 patients in the analysis, the mean (SD) age was 36.7 (14.3) years, and 15 752 (48.8%) were male. In the validation sample, the treatment success rate (SE) was 51.7% (1.0%) under the ITR and was 44.5% (0.5%) in the observed population (Z = 7.1; P < .001). The estimated treatment success if all patients were given a prescription for 1 medication was significantly lower for each of the 13 medications than under the ITR (Z = 4.2-16.8; all P < .001). Aripiprazole (3088 [31.9%]) and amisulpride (2920 [30.2%]) were the medications most often recommended by the ITR. Only 1054 patients (10.9%) received ITR-recommended medications. Observed treatment success, although lower than the success under the ITR, was nonetheless significantly higher than if medications had been randomized (44.5% [SE, 0.55%] vs 41.3% [SE, 0.4%]; Z = 6.9; P < .001), although only marginally higher than if medications had been randomized in their observed population proportions (44.5% [SE, 0.5%] vs 43.5% [SE, 0.4%]; Z = 2.2; P = .03]).

CONCLUSIONS AND RELEVANCE

These results suggest that an ITR may be associatded with an increase in the treatment success rate among patients with first-episode schizophrenia, but experimental evaluation is needed to confirm this possibility. If confirmed, model refinement that investigates biomarkers, clinical observations, and patient reports as additional predictors in iterative pragmatic trials would be needed before clinical implementation.

Pharmacogenetics in Psychiatry

Mental illness represents a major health issue both at the individual and at the socioeconomical level. This is partly due to the current suboptimal treatment options: existing psychotropic medications, including antidepressants, antipsychotics, and mood stabilizers, are effective only in a subset of patients or produce partial response and they are often associated with debilitating side effects that discourage adherence. Pharmacogenetics is the study of how genetic information impacts on drug response/side effects with the goal to provide tailored treatments, thereby maximizing efficacy and tolerability. The first pharmacogenetic studies focused on candidate genes, previously known to be relevant to the pharmacokinetics and pharmacodynamics of psychotropic drugs. Results were mainly inconclusive, but some replicated candidates were identified and included as pharmacogenetic biomarkers in drug labeling and in some commercial kits. With the advent of the genomic revolution, it became possible to study the genetic variation on an unprecedented scale, throughout the whole genome with no need of a priori hypothesis. This may lead to the personalized prescription of existing medications and potentially to the development of innovative ones, thanks to new insights into the genetics of mental illness. Promising findings were obtained, but methods for the generation and analysis of genome-wide and sequencing data are still in evolution. Future pharmacogenetic tests may consist of hundreds/thousands of polymorphisms throughout the genome or selected pathways in order to take into account the complex interactions across variants in a number of genes.