Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial

Background: Anhedonia remains a difficult-to-treat symptom and has been associated with poor clinical course transdiagnostically. Here, we applied machine learning models to individualized neural patches derived from fMRI data during the Monetary Incentive Delay Task in anhedonic participants (N = 6...

Full description

Saved in:
Bibliographic Details
Main Authors: Matthew D. Sacchet, Joseph L. Valenti, Poorvi Keshava, Shane W. Walsh, Moria J. Smoski, Andrew D. Krystal, Diego A. Pizzagalli
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Journal of Mood and Anxiety Disorders
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2950004425000239
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849732681176186880
author Matthew D. Sacchet
Joseph L. Valenti
Poorvi Keshava
Shane W. Walsh
Moria J. Smoski
Andrew D. Krystal
Diego A. Pizzagalli
author_facet Matthew D. Sacchet
Joseph L. Valenti
Poorvi Keshava
Shane W. Walsh
Moria J. Smoski
Andrew D. Krystal
Diego A. Pizzagalli
author_sort Matthew D. Sacchet
collection DOAJ
description Background: Anhedonia remains a difficult-to-treat symptom and has been associated with poor clinical course transdiagnostically. Here, we applied machine learning models to individualized neural patches derived from fMRI data during the Monetary Incentive Delay Task in anhedonic participants (N = 67) recruited for a clinical trial examining K-opioid receptor (KOR) antagonism in the treatment of anhedonia. Methods: Nine ensemble models were estimated using cortical, subcortical, and combined cortical subcortical features from individualized functional topographies to predict changes in symptoms of overall psychopathology (anhedonia, depression, anxiety). Analyses were performed on the KOR (N = 33) and placebo (N = 34) group. Results: Initial models showed that only subcortical data predicting depression and anxiety symptom change had a significant Spearman correlation between veridical and predicted data (rho = 0.480 and rho = 0.415 respectively). Next, leave-one-out-cross-validation (LOOCV) showed that the best-performing models comprised only the subcortical individualized systems data, which correlated with clinical change for depression and anxiety scores for the KOR group with significantly higher accuracy (rho = 0.634 and rho = 0.562, respectively) compared to the placebo group (rho = 0.294 and rho = 0.034, respectively). Further, 25 subcortical neural features were identified based on correlation and ensemble determined importance in driving prediction. Final models for both depression and anxiety showed an overall higher representation of the dorsal attention network. Cortical and combined cortical-subcortical feature data showed no significant improvement in prediction of clinical change between the two groups. Conclusion: Using an ensemble of machine learning approaches, we identified individual differences in subcortical individualized systems data that predicted clinical change that was specific to KOR antagonism.
format Article
id doaj-art-3304fc5c4d1d4920bc08cb5e7fb3ecb1
institution DOAJ
issn 2950-0044
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Journal of Mood and Anxiety Disorders
spelling doaj-art-3304fc5c4d1d4920bc08cb5e7fb3ecb12025-08-20T03:08:17ZengElsevierJournal of Mood and Anxiety Disorders2950-00442025-09-011110012610.1016/j.xjmad.2025.100126Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trialMatthew D. Sacchet0Joseph L. Valenti1Poorvi Keshava2Shane W. Walsh3Moria J. Smoski4Andrew D. Krystal5Diego A. Pizzagalli6Meditation Research Program, Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; Center for Depression, Anxiety and Stress Research, McLean Hospital, Harvard Medical School, Belmont, MA, USA; Correspondence to: 149 13th St., Charlestown, MA 02129-4522, USA.Meditation Research Program, Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USAMeditation Research Program, Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USAMeditation Research Program, Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USAPsychiatry and Behavioral Sciences, Duke University, Durham, NC, USADepartment of Psychiatry, University of California, San Francisco, San Francisco, CA, USACenter for Depression, Anxiety and Stress Research, McLean Hospital, Harvard Medical School, Belmont, MA, USABackground: Anhedonia remains a difficult-to-treat symptom and has been associated with poor clinical course transdiagnostically. Here, we applied machine learning models to individualized neural patches derived from fMRI data during the Monetary Incentive Delay Task in anhedonic participants (N = 67) recruited for a clinical trial examining K-opioid receptor (KOR) antagonism in the treatment of anhedonia. Methods: Nine ensemble models were estimated using cortical, subcortical, and combined cortical subcortical features from individualized functional topographies to predict changes in symptoms of overall psychopathology (anhedonia, depression, anxiety). Analyses were performed on the KOR (N = 33) and placebo (N = 34) group. Results: Initial models showed that only subcortical data predicting depression and anxiety symptom change had a significant Spearman correlation between veridical and predicted data (rho = 0.480 and rho = 0.415 respectively). Next, leave-one-out-cross-validation (LOOCV) showed that the best-performing models comprised only the subcortical individualized systems data, which correlated with clinical change for depression and anxiety scores for the KOR group with significantly higher accuracy (rho = 0.634 and rho = 0.562, respectively) compared to the placebo group (rho = 0.294 and rho = 0.034, respectively). Further, 25 subcortical neural features were identified based on correlation and ensemble determined importance in driving prediction. Final models for both depression and anxiety showed an overall higher representation of the dorsal attention network. Cortical and combined cortical-subcortical feature data showed no significant improvement in prediction of clinical change between the two groups. Conclusion: Using an ensemble of machine learning approaches, we identified individual differences in subcortical individualized systems data that predicted clinical change that was specific to KOR antagonism.http://www.sciencedirect.com/science/article/pii/S2950004425000239Individualized brain mappingMachine learningSelective kappa-opioid antagonismFunctional brain systemsTreatment predictionAnhedonia
spellingShingle Matthew D. Sacchet
Joseph L. Valenti
Poorvi Keshava
Shane W. Walsh
Moria J. Smoski
Andrew D. Krystal
Diego A. Pizzagalli
Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial
Journal of Mood and Anxiety Disorders
Individualized brain mapping
Machine learning
Selective kappa-opioid antagonism
Functional brain systems
Treatment prediction
Anhedonia
title Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial
title_full Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial
title_fullStr Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial
title_full_unstemmed Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial
title_short Individualized functional brain mapping machine learning prediction of symptom-change resulting from selective kappa-opioid antagonism in an anhedonic sample from a Fast-Fail trial
title_sort individualized functional brain mapping machine learning prediction of symptom change resulting from selective kappa opioid antagonism in an anhedonic sample from a fast fail trial
topic Individualized brain mapping
Machine learning
Selective kappa-opioid antagonism
Functional brain systems
Treatment prediction
Anhedonia
url http://www.sciencedirect.com/science/article/pii/S2950004425000239
work_keys_str_mv AT matthewdsacchet individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial
AT josephlvalenti individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial
AT poorvikeshava individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial
AT shanewwalsh individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial
AT moriajsmoski individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial
AT andrewdkrystal individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial
AT diegoapizzagalli individualizedfunctionalbrainmappingmachinelearningpredictionofsymptomchangeresultingfromselectivekappaopioidantagonisminananhedonicsamplefromafastfailtrial