Rough-set based learning methods: A case study to assess the relationship between the clinical delivery of cannabinoid medicine for anxiety, depression, sleep, patterns and predictability
Bibliographic record
Abstract
COVID-19 is an unprecedented health crisis causing a great deal of stress and mental health challenges in populations in Canada. Recently, research is emerging highlighting the potential of cannabinoids’ beneficial effects related to anxiety, mood, and sleep disorders as well as pointing to an increased use of medicinal cannabis since COVID-19 was declared a pandemic. Furthermore, evidence points to a correlation between mental health and sleep patterns. The objective of this research is threefold: i) to assess the relationship of the clinical delivery of cannabinoid medicine, by utilizing machine learning, to anxiety, depression and sleep scores; ii) to discover patterns based on patient features such as specific cannabis recommendations, diagnosis information, decreasing/increasing levels of clinical assessment tools (GAD7, PHQ9 and PSQI) scores over a period of time (including during the COVID timeline); and iii) to predict whether new patients could potentially experience either an increase or decrease in clinical assessment tool scores. The dataset for this thesis was derived from patient visits to Ekosi Health Centres in Manitoba, Canada and Ontario, Canada from January, 2019 to April, 2021. Extensive pre-processing and feature engineering was performed. To determine the outcome of a patients treatment, a class feature (Worse, Better, or No Change) indicative of their progress or lack thereof due to the treatment received was introduced. Three well-known supervised machine learning models (tree-based, rule-based and nearest neighbour) were trained on the patient dataset. In addition, seven rough and rough-fuzzy hybrid methods were also trained on the same dataset. All experiments were conducted using a 10-fold CV method. Sensitivity and specificity measures were higher in all classes with rough and rough-fuzzy hybrid methods. The highest accuracy of 99.15% was obtained using the rule-based rough-set learning method.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.016 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".