The changing role of substances: trends, characteristics of individuals and prior healthcare utilization among individuals with accidental substance-related toxicity deaths in Ontario Canada

by Shaleesa Ledlie, Alice Holton, Pamela Leece, Bisola Hamzat, Joanna Yang, Gillian Kolla, Nikki Bozinoff, Rob Boyd, Mike Franklyn, Ashley Smoke, Paul Newcombe, Tara Gomes

Objective

To investigate trends and the circumstances surrounding fatal substance-related toxicities directly attributed to alcohol, stimulants, benzodiazepines or opioids and combinations of substances in Ontario, Canada.

Methods

We conducted a population-based cross-sectional study of all accidental substance-related toxicity deaths in Ontario, Canada from January 1, 2018 to June 30, 2022. We reported monthly rates of substance-related toxicity deaths and investigated the combination of substances most commonly involved in deaths. Demographic characteristics, location of incident, and prior healthcare encounters for non-fatal toxicities and substance use disorders were examined.

Results

Overall, 10,022 accidental substance-related toxicity deaths occurred, with the annual number of deaths nearly doubling between the first and last 12 months of the study period (N = 1,570–2,702). Opioids were directly involved in the majority of deaths (84.1%; N = 8,431), followed by stimulants (60.9%; N = 6,108), alcohol (13.4%; N = 1,346) and benzodiazepines (7.8%; N = 782). In total, 56.9% (N = 5,698) of deaths involved combinations of substances. Approximately one-fifth of individuals were treated in a hospital setting for a substance-related toxicity in the past year, with the majority being opioid-related (17.4%; N = 1,748). Finally, 60.9% (N = 6,098) of people had a substance use disorder diagnosis at time of death.

Conclusions

Our study shows not only the enormous loss of life from substance-related toxicities but also the growing importance of combinations of substances in these deaths. A large proportion of people had previously interacted within an hospital setting for prior substance-related toxicity events or related to a substance use disorder, representing important missed intervention points in providing appropriate care.

Enhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies

by Mehdi Hosseinzadeh, Amir Haider, Mazhar Hussain Malik, Mohammad Adeli, Olfa Mzoughi, Entesar Gemeay, Mokhtar Mohammadi, Hamid Alinejad-Rokny, Parisa Khoshvaght, Thantrira Porntaveetus, Amir Masoud Rahmani

This paper seeks to enhance the performance of Mel Frequency Cepstral Coefficients (MFCCs) for detecting abnormal heart sounds. Heart sounds are first pre-processed to remove noise and then segmented into S1, systole, S2, and diastole intervals, with thirteen MFCCs estimated from each segment, yielding 52 MFCCs per beat. Finally, MFCCs are used for heart sound classification. For that purpose, a single classifier and an innovative ensemble classifier strategy are presented and compared. In the single classifier strategy, the MFCCs from nine consecutive beats are averaged to classify heart sounds by a single classifier (either a support vector machine (SVM), the k nearest neighbors (kNN), or a decision tree (DT)). Conversely, the ensemble classifier strategy employs nine classifiers (either nine SVMs, nine kNN classifiers, or nine DTs) to individually assess beats as normal or abnormal, with the overall classification based on the majority vote. Both methods were tested on a publicly available phonocardiogram database. The heart sound classification accuracy was 91.95% for the SVM, 91.9% for the kNN, and 87.33% for the DT in the single classifier strategy. Also, the accuracy was 93.59% for the SVM, 91.84% for the kNN, and 92.22% for the DT in the ensemble classifier strategy. Overall, the results demonstrated that MFCCs were more effective than other features, including time, time-frequency, and statistical features, evaluated in similar studies. In addition, the ensemble classifier strategy improved the accuracies of the DT and the SVM by 4.89% and 1.64%, implying that the averaging of MFCCs across multiple phonocardiogram beats in the single classifier strategy degraded the important cues that are required for detecting the abnormal heart sounds, and therefore should be avoided.