Precision Psychiatry Applications with Pharmacogenomics: Artificial Intelligence and Machine Learning Approaches

Lin, Eugene; Lin, Chih-Chien; Lane, Hsien Yuan

doi:10.3390/ijms21030969

Cited by 84 publications

(65 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, it has been reported that married patients with MDD responded better to antidepressants as compared to unmarried ones [ 18 ]. Possible explanations for the discrepancies regarding marital status may be due to inadequate sample sizes, distinct study designs, diverse populations, and various confounding effects [ 1 , 19 ].…”

Section: Discussionmentioning

confidence: 99%

“…Nowadays researchers have been making significant progress in the interdisciplinary fields of pharmacogenomics, machine learning, and psychiatry [ 1 , 2 , 3 ]. In the arena of pharmacogenomics, the goal of machine learning research is to provide predictive algorithms that can in general help facilitate the investigation of how genetic variants and clinical variables can influence an individual’s treatment outcomes to drugs [ 1 , 2 , 3 ]. Latest advancements in machine learning algorithms have demonstrated their promising potentials with respect to pharmacogenomics for patients with psychiatric disorders [ 1 , 2 , 3 ].…”

Section: Introductionmentioning

confidence: 99%

“…In the arena of pharmacogenomics, the goal of machine learning research is to provide predictive algorithms that can in general help facilitate the investigation of how genetic variants and clinical variables can influence an individual’s treatment outcomes to drugs [ 1 , 2 , 3 ]. Latest advancements in machine learning algorithms have demonstrated their promising potentials with respect to pharmacogenomics for patients with psychiatric disorders [ 1 , 2 , 3 ]. For instance, machine learning approaches such as multi-layer feedforward neural networks (MFNNs) have been utilized to infer clinical treatment outcomes in patients with major depressive disorder (MDD) treated with antidepressants by using clinical characteristics and genetic variants such as single nucleotide polymorphisms (SNPs) [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework

et al. 2020

Self Cite

View full text Add to dashboard Cite

In the wake of recent advances in machine learning research, the study of pharmacogenomics using predictive algorithms serves as a new paradigmatic application. In this work, our goal was to explore an ensemble machine learning approach which aims to predict probable antidepressant treatment response and remission in major depressive disorder (MDD). To discover the status of antidepressant treatments, we established an ensemble predictive model with a feature selection algorithm resulting from the analysis of genetic variants and clinical variables of 421 patients who were treated with selective serotonin reuptake inhibitors. We also compared our ensemble machine learning framework with other state-of-the-art models including multi-layer feedforward neural networks (MFNNs), logistic regression, support vector machine, C4.5 decision tree, naïve Bayes, and random forests. Our data revealed that the ensemble predictive algorithm with feature selection (using fewer biomarkers) performed comparably to other predictive algorithms (such as MFNNs and logistic regression) to derive the perplexing relationship between biomarkers and the status of antidepressant treatments. Our study demonstrates that the ensemble machine learning framework may present a useful technique to create bioinformatics tools for discriminating non-responders from responders prior to antidepressant treatments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to the heterogeneity and complexity of MDD, single domain approaches just implementing one kind of parameter were of limited success [81]. Therefore, in the recent years, the field of personalized medicine and precision psychiatry proceeded to the application of artifical intelligence and machine-learning models [82,83] combining multi-variate data sets [75], and implementing biological and clinical patient profiles [84] in order to predict treatment outcome for psychiatric disorders in general, and MDD in particular.…”

Section: Exploring Predictors Of Treatment Responsementioning

confidence: 99%

Schema therapy versus cognitive behavioral therapy versus individual supportive therapy for depression in an inpatient and day clinic setting: study protocol of the OPTIMA-RCT

et al. 2020

View full text Add to dashboard Cite

Background Major depressive disorder represents (MDD) a major cause of disability and disease burden. Beside antidepressant medication, psychotherapy is a key approach of treatment. Schema therapy has been shown to be effective in the treatment of psychiatric disorders, especially personality disorders, in a variety of settings and patient groups. Nevertheless, there is no evidence on its effectiveness for MDD in an inpatient nor day clinic setting and little is known about the factors that drive treatment response in such a target group. Methods In the current protocol, we outline OPTIMA (OPtimized Treatment Identification at the MAx Planck Institute): a single-center randomized controlled trial of schema therapy as a treatment approach for MDD in an inpatient and day clinic setting. Over the course of 7 weeks, we compare schema therapy with cognitive behavioral therapy and individual supportive therapy, conducted in individual and group sessions and with no restrictions regarding concurrent antidepressant medication, thus approximating real-life treatment conditions. N = 300 depressed patients are included. All study therapists undergo a specific training and supervision and therapy adherence is assessed. Primary outcome is depressive symptom severity as self-assessment (Beck Depression Inventory-II) and secondary outcomes are clinical ratings of MDD (Montgomery-Asberg Depression Rating Scale), recovery rates after 7 weeks according to the Munich-Composite International Diagnostic Interview, general psychopathology (Brief Symptom Inventory), global functioning (World Health Organization Disability Assessment Schedule), and clinical parameters such as dropout rates. Further parameters on a behavioral, cognitive, psychophysiological, and biological level are measured before, during and after treatment and in 2 follow-up assessments after 6 and 24 months after end of treatment. Discussion To our knowledge, the OPTIMA-Trial is the first to investigate the effectiveness of schema therapy as a treatment approach of MDD, to investigate mechanisms of change, and explore predictors of treatment response in an inpatient and day clinic setting by using such a wide range of parameters. Insights from OPTIMA will allow more integrative approaches of psychotherapy of MDD. Especially, the identification of intervention-specific markers of treatment response can improve evidence-based clinical decision for individualizing treatment. Trial registration Identifier on clinicaltrials.gov: NCT03287362; September, 12, 2017

show abstract

“…Pharmacogenomics, a study of genomic influence in an individual's response to drug, highlights inter-individual differences in drug response and contributes to developing precision medicine; a customized treatment decision tailored for an individual based on his/her genetic profile [115]. In psychiatry, the current practice in line with this idea includes repurposing drugs via off-label prescribing [116].…”

Section: Drug Repurposing and Precision Medicinementioning

confidence: 99%

Integrative Omics for Informed Drug Repurposing: Targeting CNS Disorders

Shukla

Henkel

Alganem

et al. 2020

Preprint

View full text Add to dashboard Cite

The treatment of CNS disorders, and in particular psychiatric illnesses, lacks disease-altering therapeutics for many conditions. This is likely due to regulatory challenges involving the high cost and slow-pace of drug development for CNS disorders as well as due to limited understanding of disease causality. Repurposing drugs for new indications have lower cost and shorter development timeline compared to that of de novo drug development. Historically, empirical drug-repurposing is a standard practice in psychiatry; however, recent advances in characterizing molecules with their structural and transcriptomic signatures along with ensemble of data analysis approaches, provides informed and cost-effective repurposing strategies that ameliorate the regulatory challenges. In addition, the potential to incorporate ontological approaches along with signature-based repurposing techniques addresses the various knowledge-based challenges associated with CNS drug development. In this review we primarily discuss signature-based in silico approaches to drug repurposing, and its integration with data science platforms for evidence-based drug repurposing. We contrast various in silico and empirical approaches and discuss possible avenues to improve the clinical relevance.These concepts provide a promising new translational avenue for developing new therapies for difficult to treat disorders, and offer the possibility of connecting drug discovery platforms and big data analytics with personalized disease signatures.3

show abstract

Precision Psychiatry Applications with Pharmacogenomics: Artificial Intelligence and Machine Learning Approaches

Cited by 84 publications

References 76 publications

Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework

Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework

Schema therapy versus cognitive behavioral therapy versus individual supportive therapy for depression in an inpatient and day clinic setting: study protocol of the OPTIMA-RCT

Integrative Omics for Informed Drug Repurposing: Targeting CNS Disorders

Contact Info

Product

Resources

About