Comparison of Crude Population-Level Indicators of Opioid Use and Related Harm in New Zealand and Ontario (Canada)

Artificial intelligence based health indicator extraction and disease symptoms identification using medical hypothesis models

Patient health record analysis models assist the medical field to understand the current stands and medical needs. Similarly, collecting and analyzing the disease features are the best practice for encouraging medical researchers to understand the research problems. Various research works evolve the way of medical data analysis schemes to know the actual challenges against the diseases. The computer-based diagnosis models and medical data analysis models are widely applied to have a better understanding of different diseases. Particularly, the field of medical electronics needs appropriate health indicator extraction models in near future. The existing medical schemes support baseline solutions but lack optimal hypothesis-based solutions. This work describes the optimal hypothesis model and Akin procedures for health record users, to aid health sectors in clinical decision-making on health indications. This work proposes Medical Hypothesis and Health Indicators Extraction from Electronic Medical Records (EMR) and International Classification of Diseases (ICD-10) patient examination database using the Akin Method and Friendship method. In this Health Indicators and Disease Symptoms Extraction (HIDSE), the evidence checking procedures find and collect all possible medical evidence from the existing patient examination report. Akin Method is making the hypothesis decision from count-based evidence principles. The health indicators extraction scheme extracts all relevant information based on the health indicators query and partial input. Similarly, the friendship method is used for making information associations between medical data attributes. This Akin-Friendship model helps to build hypothesis structures and trait-based feature extraction principles. This is called as Composite Akin Friendship Model (CAFM). This proposed model consists of various test cases for developing the medical hypothesis systems. On the other hand, it provides limited accuracy in disease classification. In this regard, the proposed HIDSE implements Deep Learning (DL) based Akin Friendship Method (DLAFM) for improving the accuracy of this medical hypothesis model. The proposed DLAFM, Convolutional Neural Networks (CNN) associated Legacy Prediction Model for Health Indicator (LPHI) is developed to tune the CAFM principles. The results show the proposed health indicator extraction scheme has 8-10% of better system performance than other existing techniques.

Patterns, trends and determinants of medical opioid utilization in Canada 2005-2020: characterizing an era of intensive rise and fall

BACKGROUND

Into the 21st century, the conflation of high rates of chronic pain, systemic gaps in treatment availability and access, and the arrival of potent new opioid medications (e.g., slow-release oxycodone) facilitated strong increases in medical opioid dispensing in Canada. These persisted until post-2010 alongside rising opioid-related adverse (e.g., morbidity/mortality) outcomes. We examine patterns, trends and determinants of opioid dispensing in Canada, and specifically its 10 provinces, for the years 2005-2020.

METHODS

Raw data on prescription opioid dispensing were obtained from a large national community-based pharmacy database (IQVIA/Compuscript), converted into Defined-Daily-Doses/1,000 population/day for 'strong' and 'weak' opioid categories per standard methods. Dispensing by opioid category and formulations by province/year was assessed descriptively; regression analysis was applied to examine possible segmentation of over-time strong opioid dispensing.

RESULTS

All provinces reported starkly increasing strong opioid dispensing peaking 2011-2016, and subsequent marked declines. About half reported lower strong opioid dispensing in 2020 compared to 2005, with continuous inter-provincial differences of > 100 %; weak opioids also declined post-2011/12. Segmented regression suggests breakpoints for strong opioids in 2011/12 and 2015/16, coinciding with main interventions (e.g., selective opioid delisting, new prescribing guidelines) towards more restrictive opioid utilization control.

CONCLUSIONS

We characterized an era of marked rise and fall, while featuring stark inter-provincial heterogeneity in opioid dispensing in Canada. While little evidence for improvements in pain care outcomes exists, the starkly inverting opioid utilization have been associated with extensive population-level harms (e.g., misuse, morbidity, mortality) over-time. This national case study raises fundamental questions for opioid-related health policy and practice.