2019
DOI: 10.1093/schbul/sbz105
|View full text |Cite
|
Sign up to set email alerts
|

Using Machine Learning in Psychiatry: The Need to Establish a Framework That Nurtures Trustworthiness

Abstract: The rapid embracing of artificial intelligence in psychiatry has a flavor of being the current “wild west”; a multidisciplinary approach that is very technical and complex, yet seems to produce findings that resonate. These studies are hard to review as the methods are often opaque and it is tricky to find the suitable combination of reviewers. This issue will only get more complex in the absence of a rigorous framework to evaluate such studies and thus nurture trustworthiness. Therefore, our paper discusses t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
43
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
7
1

Relationship

2
6

Authors

Journals

citations
Cited by 41 publications
(43 citation statements)
references
References 14 publications
0
43
0
Order By: Relevance
“…Naturally, conducting mental state assessments outside of the controlled setting comes with several practical, technical and legal challenges, which are solvable through interdisciplinary collaboration 43 . For any such implementation to be possible, effective ways to monitor responses by clinical caretakers will be important 44 , both to ensure patient safety in the case of critical situations such as explicit statements of suicidality, and to make sure that the automatic processes are trustworthy and continue to generate fair and accurate scores 20 . Nonetheless, for those patients who have access to digital devices, and can operate such devices with minimal supervision, future assessment methods that embrace mobile technologies promise to be of enormous value in psychiatry and may even enhance the bond between patients and clinicians 45 .…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Naturally, conducting mental state assessments outside of the controlled setting comes with several practical, technical and legal challenges, which are solvable through interdisciplinary collaboration 43 . For any such implementation to be possible, effective ways to monitor responses by clinical caretakers will be important 44 , both to ensure patient safety in the case of critical situations such as explicit statements of suicidality, and to make sure that the automatic processes are trustworthy and continue to generate fair and accurate scores 20 . Nonetheless, for those patients who have access to digital devices, and can operate such devices with minimal supervision, future assessment methods that embrace mobile technologies promise to be of enormous value in psychiatry and may even enhance the bond between patients and clinicians 45 .…”
Section: Discussionmentioning
confidence: 99%
“…This finding is as expected and simply strengthens the notion that this automated procedure to speech provides valid scores with sufficient variability that can be leveraged in future studies to detect significant cognitive changes within patients across time (i.e., sensitive enough to be used within participants). Indeed, we note that the traditional concern about 'matching' groups in a classic clinical sense is both less necessary and more improbable for machine learning studies that specifically can leverage this enormous variability that is inherent in large and 'messy' datasets 20 .…”
Section: Verbal Retelling From Participant (Example)mentioning
confidence: 99%
“…When considering labeled data, the main aim of supervised ML, as opposed to statistical methods, is the maximization of classification/prediction accuracy, while sacrificing model explainability and rigorous statistical validation. Accordingly, recent work highlights the need to establish an ML framework in psychiatry that nurtures trustworthiness, focusing on explainability, transparency, and generalizability of the obtained models (11). This approach, regardless of the superior classification/prediction performance, is critical in order for the AI methods to be employed in diagnosis, monitoring, evaluation, and prognosis of mental illness.…”
Section: Statistical and Machine Learning Analysismentioning
confidence: 99%
“…In such circumstances, one of the greatest impacts of digital psychiatry, particularly applied artificial intelligence (AI) and machine learning (ML) (10)(11)(12)(13)(14)(15) during the ongoing COVID-19 pandemic, is their ability of early detection and prediction of HCWs' mental health deterioration, which can lead to chronic mental health disorders. Further-more, AI-based psychiatry may help mental health practitioners redefine mental illnesses more objectively than is currently done by DSM-5 (14).…”
mentioning
confidence: 99%
“…With the increase in this type of research, there are calls to create frameworks to ensure that both the methods and results are trustworthy. One such call outlines three issues, namely, explainability, transparency, and generalizability, which need to be addressed before trustworthiness can be established (Chandler et al 2020). There is also the issue of applicability for researchers as these methods can be difficult to implement and interpret for non-specialists.…”
Section: Potential Challengesmentioning
confidence: 99%