Computational approaches and machine learning for individual-level treatment predictions

Paulus, Martin P.; Thompson, Wesley K.

doi:10.1007/s00213-019-05282-4

Cited by 24 publications

(16 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite their well-described clinical 3 and neurochemical effects 4,5 , the cognitive and computational mechanisms underlying SSRI treatment effectiveness remain elusive 6,7 . This lack of a mechanistic understanding arguably compromises development of effective treatment stratification and clinical prediction models 8 .…”

mentioning

confidence: 99%

A mechanistic account of serotonin’s impact on mood

et al. 2020

View full text Add to dashboard Cite

Selective serotonin reuptake inhibitors (SSRIs) constitute a first-line antidepressant intervention, though the precise cognitive and computational mechanisms that explain treatment response remain elusive. Using week-long SSRI treatment in healthy volunteer participants, we show serotonin enhances the impact of experimentally induced positive affect on learning of novel, and reconsolidation of previously learned, reward associations. Computational modelling indicated these effects are best accounted for by a boost in subjective reward perception during learning, following a positive, but not negative, mood induction. Thus, instead of influencing affect or reward sensitivity directly, SSRIs might amplify an interaction between the two, giving rise to a delayed mood response. We suggest this modulation of affect-learning dynamics may explain the evolution of a gradual mood improvement seen with these agents and provides a novel candidate mechanism for the unfolding of serotonin’s antidepressant effects over time.

show abstract

mentioning

confidence: 99%

A mechanistic account of serotonin’s impact on mood

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This lack of strong evidence has implications for the use of AI in mental health services. In an insightful article on using AI for individual-level treatment predictions, Paulus and Thompson ( 2019 ) make several key observations and suggestions that are very relevant to the current paper. The authors summarize several meta-analyses of the weak evidence of effectiveness of mental health interventions and come to conclusions similar to those I have already stated.…”

Section: Problems and Limitations With Aimentioning

confidence: 99%

Improving Mental Health Services: A 50-Year Journey from Randomized Experiments to Artificial Intelligence and Precision Mental Health

Bickman

2020

Adm Policy Ment Health

100

View full text Add to dashboard Cite

This conceptual paper describes the current state of mental health services, identifies critical problems, and suggests how to solve them. I focus on the potential contributions of artificial intelligence and precision mental health to improving mental health services. Toward that end, I draw upon my own research, which has changed over the last half century, to highlight the need to transform the way we conduct mental health services research. I identify exemplars from the emerging literature on artificial intelligence and precision approaches to treatment in which there is an attempt to personalize or fit the treatment to the client in order to produce more effective interventions. Keywords Mental health services • Artificial intelligence • Machine learning • Precision mental health • Randomized clinical trials (RCTs) • Precision medicine "AI will bring many wonders. It may also destabilize everything from nuclear détente to human friendships. We need to think much harder about how to adapt... it is changing human knowledge, perception and reality-and, in so doing, changing the course of human history. We seek to understand it and its consequences and encourage others across the disciplines to do the same."-Kissinger et al. 2019, pp. 24-26 "AI is one of the most profound things we're working on as humanity. It's more profound than fire or electricity."-Alphabet CEO Sundar Pichai, in Thompson and Bodoni 2020. This article is part of a special issue, Festschrift for Leonard Bickman: The Future of Children's Mental Health Services.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The increasing adoption of computational approaches in cognitive neuroscience inspired the emerging discipline of computational psychiatry, which aims to better understand mental illness through computational methods with the ultimate goal of transforming such knowledge into new personalised treatment strategies (Adams, Huys, & Roiser, 2016;Browning et al, 2020;Friston, Redish, & Gordon, 2017;Huys, 2018;Huys et al, 2016;Huys, Moutoussis, & Williams, 2011;Maia & Frank, 2011;Montague, Dolan, Friston, & Dayan, 2012;Patzelt, Hartley, & Gershman, 2018;Paulus, Huys, & Maia, 2016;Paulus & Thompson, 2019;Teufel & Fletcher, 2016;Wang & Krystal, 2014;Wiecki, Poland, & Frank, 2015). For such translational endeavours to be successful, however, it is vital that computational measures capture individual characteristics reliably (Browning et al, 2020;Paulus et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Reliability of Decision-Making and Reinforcement Learning Computational Parameters

Mkrtchian

Valton

Roiser

2021

Preprint

View full text Add to dashboard Cite

Background: Computational models can offer mechanistic insight into cognition and therefore have the potential to transform our understanding of psychiatric disorders and their treatment. For translational efforts to be successful, it is imperative that computational measures capture individual characteristics reliably. To date, this issue has received little consideration. Methods: Here we examine the reliability of canonical reinforcement learning and economic models derived from two commonly used tasks. Healthy individuals (N=50) completed a restless four-armed bandit and a calibrated gambling task twice, two weeks apart. Results: Reward and punishment processing parameters from the reinforcement learning model showed fair-to-good reliability, while risk/loss aversion parameters from a prospect theory model exhibited good-to-excellent reliability. Both models were further able to predict future behaviour above chance within individuals. Conclusions: These results suggest that reinforcement learning, and particularly prospect theory measures, represent relatively reliable decision-making mechanisms, which are also unique across individuals, indicating the translational potential of clinically-relevant computational parameters for precision psychiatry.

show abstract

Computational approaches and machine learning for individual-level treatment predictions

Cited by 24 publications

References 78 publications

A mechanistic account of serotonin’s impact on mood

A mechanistic account of serotonin’s impact on mood

Improving Mental Health Services: A 50-Year Journey from Randomized Experiments to Artificial Intelligence and Precision Mental Health

Reliability of Decision-Making and Reinforcement Learning Computational Parameters

Contact Info

Product

Resources

About