update

content/en/ai-in-mental-health.md

@@ -0,0 +1,36 @@
+---
+title: "AI in mental health research"
+description: "Harmony is an AI tool for mental health research"
+date: 2024-10-07
+image: /images/blog/roc.png
+
+url: "/ai-in-mental-health/"
+---
+
+## AI in mental health research
+
+Artificial intelligence (AI) is revolutionising numerous fields, and mental health research is no exception. By harnessing the power of AI, researchers are gaining unprecedented insights into the complexities of mental health, leading to more effective interventions and treatments.
+
+One notable example of AI's impact is the development of tools like **Harmony**. This [innovative AI tool](/psychology-ai-tool/), originally funded by the Wellcome Trust as part of the [Wellcome data prize](/ai-in-mental-health/radio-podcast-about-wellcome-data-prize/) and later by UKRI, uses natural language processing (NLP) to streamline the [harmonisation of mental health questionnaires](/data-harmonisation/find-matching-and-common-items-in-questionnaires-and-surveys/). By automating this time-consuming process, Harmony enables researchers to compare data across studies more efficiently, leading to more robust and reliable [secondary data analysis](/ai-in-mental-health/ppie-for-secondary-data-analysis/).
+
+
+We have recently published a paper in BMC Psychiatry validating Harmony for real-world data:  McElroy, E., Wood, T.A., Bond, R., Mulvenna M., Shevlin M., Ploubidis G., Scopel Hoffmann M., Moltrecht B., [Using natural language processing to facilitate the harmonisation of mental health questionnaires: a validation study using real-world data](/ai-in-mental-health/bmc-psychiatry-paper/). BMC Psychiatry 24, 530 (2024). https://doi.org/10.1186/s12888-024-05954-2
+
+
+## Other uses of AI for mental health research
+
+Beyond Harmony, AI is being used in a wide range of mental health research applications:
+
+* **Predictive Modelling:** AI algorithms can analyze large datasets to identify patterns and predict future outcomes, such as the likelihood of a relapse or the effectiveness of a particular treatment.
+* **Natural Language Processing:** NLP tools can analyze text data, such as social media posts or clinical notes, to gain insights into mental health conditions and identify potential risk factors.
+* **Machine Learning:** Machine learning algorithms can be trained on vast amounts of data to develop models that can diagnose mental health conditions with greater accuracy than traditional methods.
+* **Virtual Reality:** AI-powered virtual reality experiences can be used to simulate real-world situations and provide exposure therapy for conditions like anxiety and phobias.
+
+As AI technology [continues to advance](/ai-in-mental-health/harmony-going-forward/), we can expect to see even more groundbreaking applications in mental health research. By leveraging the power of AI, researchers are paving the way for a brighter future for individuals struggling with mental health challenges. As uses of AI in mental health become more commonplace, we are expecting research funders to develop [frameworks for AI governance](/ai-in-mental-health/research-funders-ai-governance/).
+
+## Harmony events
+
+
+* [Harmony at Lifecourse seminar](/ai-in-mental-health/harmony-at-lifecourse-seminar/) - on 15 May 2024, Eoin McElroy and Bettina Moltrecht gave a seminar Harmony: A global platform for harmonisation, translation and cooperation in mental health research for the Melbourne Children’s LifeCourse Initiative seminar series.
+* [Harmony at Methodscon Futures](/ai-in-mental-health/harmony-at-methodscon-futures/) - on  11 and 12 September 2024, Bettina Moltrecht and Thomas Wood presented Harmony at Methodscon Futures in Manchester
+

content/en/blog/bmc-paper.md

@@ -23,7 +23,7 @@ We are pleased to announce the publication of a paper validating Harmony on real
 
 ## Summary of the Harmony real-world validation study
 
-Our study aimed to evaluate the effectiveness of Natural Language Processing (NLP) in [harmonising mental health questionnaires](/ces-d-vs-gad-7/) for cross-study research.
+Our study aimed to evaluate the effectiveness of Natural Language Processing (NLP) in [harmonising mental health questionnaires](/ces-d-vs-gad-7/) for cross-study research in areas such as [mental health](/ai-in-mental-health/).
 
 By comparing the semantic similarity of questionnaire items using NLP (the [Sentence-BERT transformer model](/measuring-the-performance-of-nlp-algorithms/)) with their actual correlation in a sample population, we found a moderate relationship (*r* = .48, *p* < .001) between the two measures. This suggests that NLP can accurately identify similar questions across different questionnaires. 
 

content/en/blog/data-harmonisation.md

@@ -37,7 +37,7 @@ Imagine trying to compare financial reports from different countries, each using
 
 2. **Data Cleaning and Preprocessing**: This involves cleansing the data to ensure its quality. Common tasks include correcting errors, handling missing values, removing duplicates, and addressing outliers. Preprocessing also involves standardizing data, like ensuring consistent naming conventions and formats.
 
-3. **Data Transformation**: Here, data is converted into a standardized format or structure. This could involve changing data types, normalizing values (like converting all currencies to a standard currency), standardizing date formats, or scaling measurements to a common unit. The goal is to ensure that data from different sources can be compared and analyzed together.
+3. **Data Transformation**: Here, data is converted into a standardized format or structure. This could involve changing data types, normalizing values (like converting all currencies to a standard currency), standardizing date formats, or [scaling measurements to a common unit](/data-harmonisation/find-matching-and-common-items-in-questionnaires-and-surveys/). The goal is to ensure that data from different sources can be compared and analyzed together.
 
 4. **Data Integration**: In this step, the cleaned and transformed data from various sources is merged into a single, unified dataset. This involves aligning data schemas, resolving any conflicts in data structure or content, and ensuring that data from different sources correctly corresponds and aligns with each other.
 

content/en/blog/harmony-going-forward-5-things-implementation-science-has-taught-us-to-focus-on.md

@@ -15,7 +15,7 @@ url: "/ai-in-mental-health/harmony-going-forward/"
 
 Yesterday the [Harmony team](https://harmonydata.ac.uk/team/) received the wonderful news that we are given the chance to continue working on Harmony for another six months, after which we can put ourselves forward for the final round. The [Wellcome Mental Health Data Prize](https://wellcome.org/grant-funding/schemes/wellcome-mental-health-data-prize) has chosen an unusual (for the research world) approach this time, using a “Dragon’s Den” style scheme where research teams can pitch their ideas to win funding for their [projects](https://harmonydata.ac.uk/projects-partners). We started this journey with 10 other teams around six months ago, and last week we all presented our work and pitched our vision for the next 6 months. This nontypical funding scheme challenges some of the traditionally slow university structures, and I am excited about the creativity with which the Wellcome Trust keeps the research world on its toes.
 
-As our team embarks on the prototyping journey, I am reflecting on how we can maximise the implementation success for our digital [Harmony tool](https://harmonydata.ac.uk/app/?_ga=2.55018287.544219844.1678452210-721610193.1678452210&_gl=1*7y76do*_ga*NzIxNjEwMTkzLjE2Nzg0NTIyMTA.*_ga_5B3RD8TY0P*MTY3ODQ1MjIxMC4xLjEuMTY3ODQ1MjIyNC4wLjAuMA..). I **want** Harmony to have a life post grant-funding and ensure that it has measurable impact on the wider researcher community and global mental health efforts.
+As our team embarks on the prototyping journey, I am reflecting on how we can maximise the implementation success for our digital [Harmony tool](https://harmonydata.ac.uk/app/?_ga=2.55018287.544219844.1678452210-721610193.1678452210&_gl=1*7y76do*_ga*NzIxNjEwMTkzLjE2Nzg0NTIyMTA.*_ga_5B3RD8TY0P*MTY3ODQ1MjIxMC4xLjEuMTY3ODQ1MjIyNC4wLjAuMA..). I **want** Harmony to have a life post grant-funding and ensure that it has measurable impact on the wider researcher community and [global mental health efforts](/ai-in-mental-health/).
 
 The successful implementation and [sustainability](/making-harmony-sustainable-long-term/) of digital products developed through research grant funding, has been shockingly low. We have seen this especially in the digital mental health field, where thousands of apps and platforms have been developed and only very few have been implemented and sustained in the wild. From this line of [research](https://www.psychiatrist.com/jcp/psychiatry/implementing-digital-mental-health-interventions/#ref16) and [my own work with colleagues](https://www.jmir.org/2022/11/e40347) I know that innovation and effectiveness alone are not sufficient to secure real-world adoption .
 

content/en/blog/harmony-methodscon.md

@@ -13,7 +13,7 @@ url: "/ai-in-mental-health/harmony-at-methodscon-futures/"
 ## MethodsCon in Manchester
 
 
-We will be at [MethodsCon: Futures](https://www.ncrm.ac.uk/training/MethodsCon2024) in Manchester, run by the [National Centre for Research Methods](https://www.ncrm.ac.uk/) on 11 and 12 September 2024 to present [Harmony](https://harmonydata.ac.uk/app), the NLP and AI tool we have been developing for researchers in social science, funded by Wellcome and the Economic and Social Research Council. The events take place at [The Edwardian Manchester](https://www.radissonhotels.com/en-us/hotels/radisson-collection-edwardian-manchester).
+We will be at [MethodsCon: Futures](https://www.ncrm.ac.uk/training/MethodsCon2024) in Manchester, run by the [National Centre for Research Methods](https://www.ncrm.ac.uk/) on 11 and 12 September 2024 to present [Harmony](https://harmonydata.ac.uk/app), the NLP and [AI tool](/ai-in-mental-health/) we have been developing for researchers in social science, funded by Wellcome and the Economic and Social Research Council. The events take place at [The Edwardian Manchester](https://www.radissonhotels.com/en-us/hotels/radisson-collection-edwardian-manchester).
 
 ## Methods Showcase – 11th September
 

content/en/blog/lifecourse.md

@@ -14,4 +14,4 @@ url: "/ai-in-mental-health/harmony-at-lifecourse-seminar/"
 
 {{< youtube ZPY-fPsVIE4 >}}
 
-On 15 May 2024, Eoin McElroy and Bettina Moltrecht gave a seminar *Harmony: A global platform for harmonisation, translation and cooperation in mental health research* for the [Melbourne Children's LifeCourse](https://lifecourse.melbournechildrens.com/) Initiative seminar series.
+On 15 May 2024, Eoin McElroy and Bettina Moltrecht gave a seminar *Harmony: A global platform for harmonisation, translation and cooperation in [mental health research](/ai-in-mental-health/)* for the [Melbourne Children's LifeCourse](https://lifecourse.melbournechildrens.com/) Initiative seminar series.

content/en/blog/matching-common-items.md

@@ -15,7 +15,7 @@ When researchers take on the task of analysing data from surveys and questionnai
 
 According to [Forbes](https://www.forbes.com/sites/gilpress/2016/03/23/data-preparation-most-time-consuming-least-enjoyable-data-science-task-survey-says/?sh=46f8687f6f63), researchers spend up to 80% of their time just getting data ready for analysis, and a big part of that time goes into harmonising data.
 
-The harmonisation of questionnaire data, therefore, becomes an important aspect of research. This is especially true when you’re striving for high data accuracy and comparability (as you should).
+The [harmonisation of questionnaire data](/data-harmonisation/), therefore, becomes an important aspect of research. This is especially true when you’re striving for high data accuracy and comparability (as you should).
 
 Achieving a harmonious dataset means researchers can draw reliable connections and conclusions across different studies and this boosts the credibility and impact of their work. But how do you make it happen? Let’s talk about it!
 

content/en/blog/ppie-for-secondary-data-analysis.md

@@ -14,7 +14,7 @@ url: "/ai-in-mental-health/ppie-for-secondary-data-analysis/"
 
 About one year ago I fully entered the world of secondary data analysis research – away from applied mental health research with creative data collection methods and small sample sizes, towards big data and complex analyses efforts to overcome what someone deemed not worth measuring (Wait, why are we not assessing emotion regulation in each and every study 1?) 
 
-Of course, I know we can’t measure everything and the decision of what to measure in studies is one of the hardest to make. If you put 100 mental health researchers into one room, I believe all of them would consider their research area important enough and worth measuring in a big research study, because we love what we do and we are very passionate about our research. 
+Of course, I know we can’t measure everything and the decision of what to measure in studies is one of the hardest to make. If you put 100 [mental health](/ai-in-mental-health/) researchers into one room, I believe all of them would consider their research area important enough and worth measuring in a big research study, because we love what we do and we are very passionate about our research. 
 
 I have had a fantastic past year, filled with a lot of learning, exciting new discoveries, and wonderful support from my colleagues at the [Centre for Longitudinal Studies](https://cls.ucl.ac.uk/about/) ([UCL](https://ucl.ac.uk)). Finally, last week my time had come to give back. I invited my colleagues to a “PPIE – (Patient and Public Involvement and Engagement) in Research” session. PPIE is relatively common in applied mental health research (I know, we can always do more), where researchers invite members of the public to help them decide on recruitment strategies, the design of study materials, interpretation of findings, and what infographics or other research outputs would actually matter to clients, service-users or patients. However, when it comes to less applied research areas, such as research relying primarily on secondary data analyses, my impression has been that PPIE is only very *slowly* making its way in – thereby causing a mix of real positive excitement in some of my colleagues (“I am allowed to talk to people?”) and pure anxiety and confusion in others ( Do I need to explain latent growth curve [models](https://harmonydata.ac.uk/semantic-text-matching-with-deep-learning-transformer-models) to them?).
 

content/en/blog/pydata.md

@@ -15,7 +15,7 @@ url: "/psychology-ai-tool/pydata-meetup/"
 
 Topic: **NLP and generative models for psychology research**
 
-Thomas Wood will present our work on Harmony, harmonydata.ac.uk, which is a free online tool that uses generative AI and LLMs to help psychologists analyse datasets. It uses Python, Pandas and HuggingFace Sentence Transformers to find similarities between questionnaires.
+Thomas Wood will present our work on Harmony, harmonydata.ac.uk, which is a [free online tool](/psychology-ai-tool/) that uses generative AI and LLMs to help psychologists analyse datasets. It uses Python, Pandas and HuggingFace Sentence Transformers to find similarities between questionnaires.
 
 * Psychologists and social scientists often have to match items in different questionnaires, such as "I often feel anxious" and "Feeling nervous, anxious or afraid".
 * This is called harmonisation.

content/en/blog/radio-podcast-about-wellcome-data-prize.md

@@ -12,7 +12,7 @@ url: "/ai-in-mental-health/radio-podcast-about-wellcome-data-prize/"
 ---
 
 
-The Wellcome Data Prize was recently featured on [Smile 90.4FM](https://smilefm.co.za/), a radio station in South Africa. In this episode, Inês Pote discussed the [Wellcome Data Prize in Mental Health](https://wellcome.org/grant-funding/schemes/wellcome-mental-health-data-prize). Wellcome is on the lookout for teams that develop innovative ways to use data to improve the prevention, treatment, and management of anxiety and depression in young people in South Africa.
+The Wellcome Data Prize was recently featured on [Smile 90.4FM](https://smilefm.co.za/), a radio station in South Africa. In this episode, Inês Pote discussed the [Wellcome Data Prize in Mental Health](https://wellcome.org/grant-funding/schemes/wellcome-mental-health-data-prize). Wellcome is on the lookout for teams that develop innovative ways to use data to improve the prevention, treatment, and management of [anxiety and depression](/ai-in-mental-health/) in young people in South Africa.
 
 {{< htmlcode >}}
 

content/en/blog/research-funders-ai-governance-vacuum.md

@@ -16,7 +16,7 @@ A [recent article by Sense about Science](https://senseaboutscience.org/activiti
 
 The article, titled [Research funders tackle AI governance vacuum with pragmatic guidance](https://senseaboutscience.org/activities/research-funders-tackle-ai-governance-vacuum-with-pragmatic-guidance/), discusses the alarming gap between the rapid development and adoption of AI tools, and the lack of clear frameworks for their safe and ethical use. This is particularly concerning in healthcare, where AI applications are increasingly used without established regulations.
 
-Sense about Science recognises the importance of responsible AI development. Harmony tackles a key challenge in mental health research –  **harmonising data from different studies**. 
+Sense about Science recognises the importance of responsible AI development. Harmony tackles a key challenge in [mental health research](/ai-in-mental-health/) –  **harmonising data from different studies**. 
 
 Dr. Bettina Moltrecht from UCL, who worked on Harmony and is now leading the project under the current UKRI grant, points out that "researchers need the awareness and knowledge captured in the framework for tools being developed not to become obsolete or impractical for others to pick up".