Application of machine learning to predict reduction in total PANSS score and enrich enrollment in schizophrenia clinical trials

Podichetty, Jagdeep T.; Silvola, Rebecca; Rodriguez‐Romero, Violeta; Bergstrom, Richard F.; Vakilynejad, Majid; Bies, Robert R.; Stratford, Robert E.

doi:10.1111/cts.13035

Cited by 8 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19 CPT's sister journals are also publishing on machine learning, including two articles highlighted in this issue of CPT. 20,21 What can be expected for the near future? Will we see the development of more machine learning algorithms to support therapeutic drug management and model-informed precision dosing for other categories of drugs?…”

Section: Machine Learning As a Novel Methods To Support Therapeutic Drug Management And Precision Dosingmentioning

confidence: 99%

Machine Learning as a Novel Method to Support Therapeutic Drug Management and Precision Dosing

Gelder

Vinks

2021

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Section: Machine Learning As a Novel Methods To Support Therapeutic Drug Management And Precision Dosingmentioning

confidence: 99%

Machine Learning as a Novel Method to Support Therapeutic Drug Management and Precision Dosing

Gelder

Vinks

2021

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

“…The sociodemographic and clinical characteristics of participants in included studies are presented in Table 1. Among the 28 included publications, the majority of them considered only subjects with the first episode of psychosis (FEP) [23,[28][29][30][31][32][33][34][35][36][37], while 10 studies considered patients with chronic SCZ [38][39][40][41][42][43][44][45][46][47]. The remaining selected studies included both FEP and SCZ patients [48][49][50][51][52][53][54].…”

Section: Clinical Characteristicsmentioning

confidence: 99%

“…Moreover, three studies used sMRI measures [31,49,50], three studies used EEG data [41,43,47], one study considered positron emission tomography (PET) data [54], and one study used proton magnetic resonance spectroscopy (MRS) data [36]. Conversely, eight studies used clinical and sociodemographic data as input features to the ML algorithms [23,35,37,38,40,42,44,51]. Among the multi-modality studies, different sets of features were used together as input to the ML algorithms.…”

Section: Approachesmentioning

confidence: 99%

“…The broad majority of them used changes in scores of psychotic symptom severity scales, such as the Positive and Negative Syndrome Scale (PANSS) and the Brief Psychiatric Rating Scale (BPRS), as measures of clinical improvement [28-31, 33-35, 39, 41, 43, 44, 46, 48-50, 53, 54]. In many of these studies, ML methods were applied to predict binary outcomes ("response" versus "no response", or "remission" versus "no remission") to antipsychotic treatment [28,29,32,35,39,41,43,44,46,48,49,51,54] while several studies used ML techniques for predicting continuous values such as reduction rates of PANSS and BPRS. Additionally, as the definition of treatment outcome is not merely defined by the symptomatic response, but might base on complex clinical and social domains, other measures and scales assessing specific symptoms and functioning criteria were used as labels in many studies [23, 36-38, 40, 42, 45, 47, 51, 52].…”

Section: Approachesmentioning

confidence: 99%

“…Specifically, several studies found that support vector regressor (SVR) has the highest and most consistent overall accuracy compared to different ML techniques [23,41,43,54], suggesting that SVR can deal with imbalanced datasets more effectively than other ML approaches [23,41]. Nevertheless, other studies showed that predictions on the same dataset were similar regardless of the different ML methods used [28,32,40,51], while in one study a random forest algorithm performed best relative to other approaches [44]. Finally, one study that compared different ML methods and one deep learning (DL) approach showed that the best overall performances were achieved using DL, suggesting that DL might be a promising approach for treatment predictions in patients with psychosis and supporting the development of DL-based methods in future research [39].…”

Section: Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning methods to predict outcomes of pharmacological treatment in psychosis

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

TheMPRINTHub Data, Model, Knowledge and Research Coordination Center: Bridging the gap in maternal–pediatric therapeutics research through data integration and pharmacometrics

et al. 2023

Self Cite

View full text Add to dashboard Cite

Maternal and pediatric populations have historically been considered “therapeutic orphans” due to their limited inclusion in clinical trials. Physiologic changes during pregnancy and lactation and growth and maturation of children alter pharmacokinetics (PK) and pharmacodynamics (PD) of drugs. Precision therapy in these populations requires knowledge of these effects. Efforts to enhance maternal and pediatric participation in clinical studies have increased over the past few decades. However, studies supporting precision therapeutics in these populations are often small and, in isolation, may have limited impact. Integration of data from various studies, for example through physiologically based pharmacokinetic/pharmacodynamic (PBPK/PD) modeling or bioinformatics approaches, can augment the value of data from these studies, and help identify gaps in understanding. To catalyze research in maternal and pediatric precision therapeutics, the Obstetric and Pediatric Pharmacology and Therapeutics Branch of the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) established the Maternal and Pediatric Precision in Therapeutics (MPRINT) Hub. Herein, we provide an overview of the status of maternal–pediatric therapeutics research and introduce the Indiana University‐Ohio State University MPRINT Hub Data, Model, Knowledge and Research Coordination Center (DMKRCC), which aims to facilitate research in maternal and pediatric precision therapeutics through the integration and assessment of existing knowledge, supporting pharmacometrics and clinical trials design, development of new real‐world evidence resources, educational initiatives, and building collaborations among public and private partners, including other NICHD‐funded networks. By fostering use of existing data and resources, the DMKRCC will identify critical gaps in knowledge and support efforts to overcome these gaps to enhance maternal–pediatric precision therapeutics.

show abstract

Application of machine learning to predict reduction in total PANSS score and enrich enrollment in schizophrenia clinical trials

Abstract: This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

Cited by 8 publications

References 36 publications

Machine Learning as a Novel Method to Support Therapeutic Drug Management and Precision Dosing

Machine Learning as a Novel Method to Support Therapeutic Drug Management and Precision Dosing

Machine learning methods to predict outcomes of pharmacological treatment in psychosis

TheMPRINTHub Data, Model, Knowledge and Research Coordination Center: Bridging the gap in maternal–pediatric therapeutics research through data integration and pharmacometrics

Contact Info

Product

Resources

About