Feasibility and impact of a mental health chatbot on postpartum mental health: a randomized controlled trial

Suharwardy, Sanaa; Muthiyan, Ramachandran; Leonard, Stephanie A.; Gunaseelan, Anita; Lyell, Deirdre J.; Darcy, Alison M.; Robinson, Athena; Judy, Amy E.

doi:10.1016/j.xagr.2023.100165

Cited by 20 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fitzpatrick et al [ 22 ] used a chatbot, Woebot, in young adult patients with depressive symptoms. Suharwardy et al [ 23 ] conducted studies on the use of Woebot in the context of postpartum depression. This intervention equips patients with tools from CBT and interpersonal therapy (IPT) to manage mood and anxiety.…”

Section: Resultsmentioning

confidence: 99%

“…This intervention equips patients with tools from CBT and interpersonal therapy (IPT) to manage mood and anxiety. Both studies reported a significant depressive symptomatology reduction, although Suharwardy et al [ 23 ] did not include only women with confirmed diagnosis of postpartum depression.…”

Section: Resultsmentioning

confidence: 99%

“…There are more studies specifically addressed to MDD, even though mostly recruited subjects with depressive symptomatology, not necessarily with a MDD diagnosis (Table 3 ); being more represented by adult subjects with only one study addressed to young adults [ 22 ], only one study recruiting adolescents [ 19 ] and one study included older adults [ 17 ]. Two studies were carried out on women at-risk for postpartum depression (PPD) [ 18 , 23 ]. Moreover, most studies on MDD were conducted in the USA and in a single-site and recruited a small sample size (with less than 100 recruited subjects) (Table 3 ).…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, most studies on MDD were conducted in the USA and in a single-site and recruited a small sample size (with less than 100 recruited subjects) (Table 3 ). Most DTx on MDD or depressive symptomatology have been developed based on CBT interventions, with one study based on EFMT [ 14 ] and the two only studies on PPD which integrate both CBT and IPT [ 18 , 23 ]. While only four are the published studies evaluating DTx on BD samples, with mostly recruiting a relatively small sample size (≤20 recruited subjects) and based on feasibility and/or acceptability outcomes as well as psychoeducational-based interventions (Table 3 ).…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Practical application of digital therapeutics in people with mood disorders

Orsolini,

Longo,

Volpe

2023

Current Opinion in Psychiatry

View full text Add to dashboard Cite

Digital therapeutics (DTx) offer evidence-based digitally-delivered high quality standards applications and/or softwares in the prevention, management and treatment of several medical conditions, including mood disorders. Nowadays, there are only three DTx officially approved by the Food and Drug Administration for mental conditions and there are still very few DTx developed in the context of mood disorders. The current comprehensive overview aims at providing a summary of currently published studies on DTx clinical applications in major depressive disorder (MDD), depressive symptomatology and bipolar disorder (BD), by using PubMed/MEDLINE and Scopus databases. Fifteen studies have been selected (10 on DTx in depressive symptomatology and/or MDD; 4 on BD; 1 on MDD and BD). Literature on DTx in mood disorders is still lacking, being mostly constituted by feasibility and acceptability rather than efficacy/effectiveness outcomes, particularly in BD. More studies focused on MDD compared to BD. Most DTx on MDD have been developed based on cognitive behaviour therapy interventions while on BD are based on psychoeducation. All studies assessing symptom severity improvement pre- vs. postinterventions demonstrated a significant postintervention improvement. Therefore, despite the preliminary encouraging results of studies here retrieved, their methodology is still too heterogeneous to allow comparisons and the generalizability of their findings. Further studies are warranted, in more larger samples involving multiple sites, including measures of both specific symptom effects as well as acceptability, feasibility and effectiveness in the real-world settings.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Practical application of digital therapeutics in people with mood disorders

Orsolini,

Longo,

Volpe

2023

Current Opinion in Psychiatry

View full text Add to dashboard Cite

show abstract

“…Some clinicians are favourable towards AI inclusion in crisis‐contexts (Sweeney et al, 2021) but their effectiveness and quality are yet to be determined. A recent randomized control trial of perinatal women with low mood found users tolerated and liked interacting with a chatbot, but there was no effect on their mood overall (Suharwardy et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

Could artificial intelligence write mental health nursing care plans?

Woodnutt,

Allen,

Snowden

et al. 2023

Psychiatric Ment Health Nurs

View full text Add to dashboard Cite

Accessible SummaryWhat is Known on the Subject? Artificial intelligence (AI) is freely available, responds to very basic text input (such as a question) and can now create a wide range of outputs, communicating in many languages or art forms. AI platforms like OpenAI's ChatGPT can now create passages of text that could be used to create plans of care for people with mental health needs. As such, AI output can be difficult to distinguish from human‐output, and there is a risk that its use could go unnoticed. What this Paper Adds to Existing Knowledge? Whilst it is known that AI can produce text or pass pre‐registration health‐profession exams, it is not known if AI can produce meaningful results for care delivery. We asked ChatGPT basic questions about a fictitious person who presents with self‐harm and then evaluated the quality of the output. We found that the output could look reasonable to laypersons but there were significant errors and ethical issues. There are potential harms to people in care if AI is used without an expert correcting or removing these errors. What are the Implications for Practice? We suggest that there is a risk that AI use could cause harm if it was used in direct care delivery. There is a lack of policy and research to safeguard people receiving care ‐ and this needs to be in place before AI should be used in this way. Key aspects of the role of a mental health nurse are relational and AI use may diminish mental health nurses' ability to provide safe care in its current form. Many aspects of mental health recovery are linked to relationships and social engagement, however AI is not able to provide this and may push the people who are in most need of help further away from services that assist recovery. AbstractBackgroundArtificial intelligence (AI) is being increasingly used and discussed in care contexts. ChatGPT has gained significant attention in popular and scientific literature although how ChatGPT can be used in care‐delivery is not yet known.AimsTo use artificial intelligence (ChatGPT) to create a mental health nursing care plan and evaluate the quality of the output against the authors’ clinical experience and existing guidance.Materials & MethodsBasic text commands were input into ChatGPT about a fictitious person called ‘Emily’ who presents with self‐injurious behaviour. The output from ChatGPT was then evaluated against the authors’ clinical experience and current (national) care guidance.ResultsChatGPT was able to provide a care plan that incorporated some principles of dialectical behaviour therapy, but the output had significant errors and limitations and thus there is a reasonable likelihood of harm if used in this way.DiscussionAI use is increasing in direct‐care contexts through the use of chatbots or other means. However, AI can inhibit clinician to care‐recipient engagement, ‘recycle’ existing stigma, and introduce error, which may thus diminish the ability for care to uphold personhood and therefore lead to significant avoidable harms.ConclusionUse of AI in this context should be avoided until a point where policy and guidance can safeguard the wellbeing of care recipients and the sophistication of AI output has increased. Given ChatGPT’s ability to provide superficially reasonable outputs there is a risk that errors may go unnoticed and thus increase the likelihood of patient harms. Further research evaluating AI output is needed to consider how AI may be used safely in care delivery.

show abstract