Harmony was able to reconstruct the matches of the questionnaire harmonisation tool developed by McElroy et al in 2020 with the following AUC scores: childhood 84%, adulthood 80%. Harmony was able to match the questions of the English and Portuguese GAD-7 instruments with AUC 100% and the Portuguese CBCL and SDQ with AUC 89%. Harmony was also evaluated using a variety of transformer models including MentalBERT, a publicly available pretrained language model for the mental healthcare domain.
The Wellcome Data Prize was recently featured on Smile 90.4FM, a radio station in South Africa. In this episode, Inês Pote discussed the Wellcome Data Prize in Mental Health. 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.
We are pleased to announce that the Harmony REST API is now released. The source code is at https://github.com/harmonydata/harmonyapi and the API reference PDF can be seen at https://github.com/harmonydata/harmonyapi/blob/main/docs/API_reference.pdf. Meanwhile, you can install and run Harmony Python library with pip install harmonydata How does Harmony work in layman’s terms? Harmony compares questions from different instruments by converting them to a vector representation and calculating their similarity. You can read more at https://harmonydata.
Marketing is important for an open science NLP project such as Harmony for several reasons: To raise awareness of the project and its goals. Research projects are often complex and technical, so it’s important to communicate their value and potential to a wide audience. Marketing can help to do this by creating clear and concise messaging, and by promoting the project through channels that reach the target audience. To attract contributors and collaborators.