Leveraging open data analytics and machine learning to improve mental health research and innovation: 2024 Inter-university big data challenge proceedingsIn partnership with Canadian Science Publishing, the Canadian Personalized Healthcare Innovation Network, and Underline.io
Bibliographic record
Abstract
The National Inter-University Big Data and AI Challenge is an interdisciplinary, agile educational environment that bridges the gap between traditional coursework and real-world data science applications. The challenge provides undergraduate and graduate researchers with the unique opportunity to explore the intersection of Open Data and applied scientific research by developing and presenting their research amongst peers and professionals from academia and industry. By participating, students gain skills in uncovering hidden patterns and trends in structured and unstructured data using a wide range of data analytics tools and programming languages including Python, R, and various machine learning frameworks. They also gain extensive experience with scientific communication by compiling abstracts, manuscripts, posters, and videos which ultimately culminate in a presentation on Big Data Day. The guiding theme for the 2024 National Inter-University Big Data and AI Challenge was “Leveraging Open Data Analytics and Machine Learning to Improve Mental Health Research and Innovation”. During the 2024 event, we saw over 134 participants from over 15 different institutions and 15 different degree programs learn and utilize important techniques in analytics, artificial intelligence (AI), and machine learning (ML) in order to delve into the complexities of mental health diseases and treatments. These future leaders were tasked with using Open Data to enhance our understanding of mental health and explore areas for innovation regarding mental health practice and research, gaining critical insights into this field. Various topics were investigated, ranging from the socioeconomic determinants of mental health to differential outcomes in treatment efficacy across geographic boundaries. By applying computational thinking, students explored the interplay between mental health and external factors, ultimately contributing to the development of tailored interventions and personalized care plans. We are privileged to witness the analytical capabilities of this talented generation of students, and we are confident they will demonstrate excellence throughout their academic and professional careers. The 2024 Big Data Day, the culmination of our participants’ trailblazing research, was held at the Microsoft Headquarters in Toronto. On behalf of STEM Fellowship, we extend our sincere congratulations to all students who participated in the challenge and wish them success in their future endeavours. We also want to express our appreciation to all the STEM Fellowship volunteers who support this program. We greatly appreciate the valuable collaboration and support of our partners: Research Canada, Canadian Science Publishing, CPHIN, Underline, JMIR Publications, Overleaf.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.063 | 0.062 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.009 | 0.006 |
| Scholarly communication | 0.021 | 0.013 |
| Open science | 0.004 | 0.027 |
| Research integrity | 0.008 | 0.013 |
| Insufficient payload (model declined to judge) | 0.016 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".