Artificial intelligence for family medicine research in Canada: current state and future directions: Report of the CFPC AI Working Group.

OBJECTIVE: To understand the current landscape of artificial intelligence (AI) for family medicine (FM) research in Canada, identify how the College of Family Physicians of Canada (CFPC) could support near-term positive progress in this field, and strengthen the community working in this field. COMPOSITION OF THE COMMITTEE: Members of a scientific planning committee provided guidance alongside members of a CFPC staff advisory committee, led by the CFPC-AMS TechForward Fellow and including CFPC, FM, and AI leaders. METHODS: This initiative included 2 projects. First, an environmental scan of published and gray literature on AI for FM produced between 2018 and 2022 was completed. Second, an invitational round table held in April 2022 brought together AI and FM experts and leaders to discuss priorities and to create a strategy for the future. REPORT: The environmental scan identified research related to 5 major domains of application in FM (preventive care and risk profiling, physician decision support, operational efficiencies, patient self-management, and population health). Although there had been little testing or evaluation of AI-based tools in practice settings, progress since previous reviews has been made in engaging stakeholders to identify key considerations about AI for FM and opportunities in the field. The round-table discussions further emphasized barriers to and facilitators of high-quality research; they also indicated that while there is immense potential for AI to benefit FM practice, the current research trajectory needs to change, and greater support is needed to achieve these expected benefits and to avoid harm. CONCLUSION: Ten candidate action items that the CFPC could adopt to support near-term positive progress in the field were identified, some of which an AI working group has begun pursuing. Candidate action items are roughly divided into avenues where the CFPC is well-suited to take a leadership role in tackling priority issues in AI for FM research and specific activities or initiatives the CFPC could complete. Strong FM leadership is needed to advance AI research that will contribute to positive transformation in FM.

Staffing rural emergency departments in Ontario: The who, what and where.

Introduction: The emergency department (ED) in rural communities is essential for providing care to patients with urgent medical issues and those unable to access primary care. Recent physician staffing shortages have put many EDs at risk of temporary closure. Our goal was to describe the demographics and practices of the rural physicians providing emergency medicine services across Ontario in order to inform health human resource planning. Methods: The ICES Physician database (IPDB) and Ontario Health Insurance Plan (OHIP) billing database from 2017 were used in this retrospective cohort study. Rural physician data were analysed for demographic, practice region and certification information. Sentinel billing codes (i.e., a billing code unique to a particular clinical service) were used to define 18 unique physician services. Results: A total of 1192 physicians from the IPDB met inclusion as rural generalist physicians out of a total of 14,443 family physicians in Ontario. From this physician population, a total of 620 physicians practised emergency medicine which accounted for 33% of their days worked on average. The majority of physicians practising emergency medicine were between the ages of 30 and 49 and in their first decade of practice. The most common services in addition to emergency medicine were clinic, hospital medicine, palliative care and mental health. Conclusion: This study provides insight into the practice patterns of rural physicians and the basis for better targeted physician workforce-forecasting models. A new approach to education and training pathways, recruitment and retention initiatives and rural health service delivery models is needed to ensure better health outcomes for our rural population.

Résumé Introduction: Le service d'urgence des communautés rurales est essentiel pour la prise en charge des patients présentant des problèmes médicaux urgents et de ceux qui ne peuvent accéder aux soins primaires. En raison de la récente pénurie de médecins, de nombreux services d'urgence risquent de fermer temporairement. Notre objectif était de décrire les caractéristiques démographiques et les pratiques des médecins ruraux qui fournissent des services de médecine d'urgence en Ontario afin d'éclairer la planification des ressources humaines en santé. Méthodes: La base de données des médecins de l'ICES (IPDB) et la base de données de facturation de l'assurance-santé de l'Ontario (OHIP) de 2017 ont été utilisées dans cette étude de cohorte rétrospective. Les données sur les médecins ruraux ont été analysées pour obtenir des renseignements sur la démographie, la région de pratique et la certification. Les codes de facturation sentinelle (c'est-à-dire un code de facturation unique pour un service clinique particulier) ont été utilisés pour définir 18 services médicaux uniques. Résultats: Sur un total de 14 443 médecins de famille en Ontario, 1 192 médecins de l'IPDB ont été inclus en tant que médecins généralistes ruraux. Parmi cette population de médecins, 620 pratiquaient la médecine d'urgence, ce qui représentait 33% de leurs jours de travail en moyenne. La majorité des médecins qui pratiquaient la médecine d'urgence étaient âgés de 30 à 49 ans et en étaient à leur première décennie de pratique. Les services les plus courants en plus de la médecine d'urgence étaient la clinique, la médecine hospitalière, les soins palliatifs et la santé mentale. Conclusion: Cette étude permet de mieux comprendre les modes de pratique des médecins ruraux et de jeter les bases de modèles de prévision des effectifs médicaux mieux ciblés. Une nouvelle approche des parcours d'éducation et de formation, des initiatives de recrutement et de rétention et des modèles de prestation de services de santé en milieu rural est nécessaire pour garantir de meilleurs résultats en matière de santé pour notre population rurale. Mots-clés: Médecine d'urgence, médecins ruraux, planification des ressources humaines en santé.

Utilizing deep learning and graph mining to identify drug use on Twitter data.

BACKGROUND: The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Through the analysis of a collected set of Twitter data, a model will be developed for predicting positively referenced, drug-related tweets. From this, trends and correlations can be determined. METHODS: Social media data (tweets and attributes) were collected and processed using topic pertaining keywords, such as drug slang and use-conditions (methods of drug consumption). Potential candidates were preprocessed resulting in a dataset of 3,696,150 rows. The predictive classification power of multiple methods was compared including SVM, XGBoost, BERT and CNN-based classifiers. For the latter, a deep learning approach was implemented to screen and analyze the semantic meaning of the tweets. RESULTS: To test the predictive capability of the model, SVM and XGBoost were first employed. The results calculated from the models respectively displayed an accuracy of 59.33% and 54.90%, with AUC's of 0.87 and 0.71. The values show a low predictive capability with little discrimination. Conversely, the CNN-based classifiers presented a significant improvement, between the two models tested. The first was trained with 2661 manually labeled samples, while the other included synthetically generated tweets culminating in 12,142 samples. The accuracy scores were 76.35% and 82.31%, with an AUC of 0.90 and 0.91. Using association rule mining in conjunction with the CNN-based classifier showed a high likelihood for keywords such as "smoke", "cocaine", and "marijuana" triggering a drug-positive classification. CONCLUSION: Predictive analysis with a CNN is promising, whereas attribute-based models presented little predictive capability and were not suitable for analyzing text of data. This research found that the commonly mentioned drugs had a level of correspondence with frequently used illicit substances, proving the practical usefulness of this system. Lastly, the synthetically generated set provided increased accuracy scores and improves the predictive capability.

SURF: identifying and allocating resources during Out-of-Hospital Cardiac Arrest.

BACKGROUND: When an Out-of-Hospital Cardiac Arrest (OHCA) incident is reported to emergency services, the 911 agent dispatches Emergency Medical Services to the location and activates responder network system (RNS), if the option is available. The RNS notifies all the registered users in the vicinity of the cardiac arrest patient by sending alerts to their mobile devices, which contains the location of the emergency. The main objective of this research is to find the best match between the user who could support the OHCA patient. METHODS: For performing matching among the user and the AEDs, we used Bipartite Matching and Integer Linear Programming. However, these approaches take a longer processing time; therefore, a new method Preprocessed Integer Linear Programming is proposed that solves the problem faster than the other two techniques. RESULTS: The average processing time for the experimentation data was   1850 s using Bipartite matching,   32 s using the Integer Linear Programming and  2 s when using the Preprocessed Integer Linear Programming method. The proposed algorithm performs matching among users and AEDs faster than the existing matching algorithm and thus allowing it to be used in the real world. CONCLUSION: This research proposes an efficient algorithm that will allow matching of users with AED in real-time during cardiac emergency. Implementation of this system can help in reducing the time to resuscitate the patient.

Assisting the Non-invasive Diagnosis of Liver Fibrosis Stages using Machine Learning Methods.

Fibrosis is a significant indication of chronic liver diseases often due to hepatitis C Virus. It is becoming a global concern as a result of the rapid increase in the number of HCV infected patients, the high cost and flaws associated with the assessment process of liver fibrosis. This study aims to determine the features that significantly contribute to the identification of the stages of liver fibrosis and to generate rules to assist physicians during the treatment of the patients as a clinically non-invasive approach. Also, the performance of different Multi-layered Perceptron (MLP), Random Forest, and Logistic Regression classifiers are estimated and compared for the full and reduced feature sets. Decision Tree produced 28 rules in contrast with previous research work where 98002 rules had been generated from the same dataset with an accuracy rate of approximately 99.97%. The resulting rules of this study achieved a prediction accuracy for the histological staging of liver fibrosis of 97.45%. Among all the machine learning methods, MLP achieved the highest accuracy rate.