Using Primary Care Clinical Text Data and Natural Language Processing to Identify Indicators of COVID-19 in Toronto, Canada.

The objective of this study was to investigate whether a rule-based natural language processing (NLP) system, applied to primary care clinical text data, could be used to monitor COVID-19 viral activity in Toronto, Canada. We employed a retrospective cohort design. We included primary care patients with a clinical encounter between January 1, 2020 and December 31, 2020 at one of 44 participating clinical sites. During the study timeframe, Toronto first experienced a COVID-19 outbreak between March-2020 and June-2020; followed by a second viral resurgence from October-2020 through December-2020. We used an expert derived dictionary, pattern matching tools and contextual analyzer to classify primary care documents as 1) COVID-19 positive, 2) COVID-19 negative, or 3) unknown COVID-19 status. We applied the COVID-19 biosurveillance system across three primary care electronic medical record text streams: 1) lab text, 2) health condition diagnosis text and 3) clinical notes. We enumerated COVID-19 entities in the clinical text and estimated the proportion of patients with a positive COVID-19 record. We constructed a primary care COVID-19 NLP-derived time series and investigated its correlation with independent/external public health series: 1) lab confirmed COVID-19 cases, 2) COVID-19 hospitalizations, 3) COVID-19 ICU admissions, and 4) COVID-19 intubations. A total of 196,440 unique patients were observed over the study timeframe, of which 4,580 (2.3%) had at least one positive COVID-19 document in their primary care electronic medical record. Our NLP-derived COVID-19 time series describing the temporal dynamics of COVID-19 positivity status over the study timeframe demonstrated a pattern/trend which strongly mirrored that of other external public health series under investigation. We conclude that primary care text data passively collected from electronic medical record systems represent a high quality, low-cost source of information for monitoring/surveilling COVID-19 impacts on community health.

Socioeconomic and immigration status and COVID-19 testing in Toronto, Ontario: retrospective cross-sectional study.

BACKGROUND: Preliminary evidence suggests that individuals living in lower income neighbourhoods are at higher risk of COVID-19 infection. The relationship between sociodemographic characteristics and COVID-19 risk warrants further study. METHODS: We explored the association between COVID-19 test positivity and patients' socio-demographic variables, using neighborhood sociodemographic data collected retrospectively from two COVID-19 Assessment Centres in Toronto, ON. RESULTS: Eighty-three thousand four hundred forty three COVID-19 tests completed between April 5-September 30, 2020, were analyzed. Individuals living in neighbourhoods with the lowest income or highest concentration of immigrants were 3.4 (95% CI: 2.7 to 4.9) and 2.5 (95% CI: 1.8 to 3.7) times more likely to test positive for COVID-19 than those in highest income or lowest immigrant neighbourhoods, respectively. Testing was higher among individuals from higher income neighbourhoods, at lowest COVID-19 risk, compared with those from low-income neighbourhoods. CONCLUSIONS: Targeted efforts are needed to improve testing availability in high-risk regions. These same strategies may also ensure equitable COVID-19 vaccine delivery.

Bedtime versus morning use of antihypertensives for cardiovascular risk reduction (BedMed): protocol for a prospective, randomised, open-label, blinded end-point pragmatic trial.

INTRODUCTION: Sleep-time blood pressure correlates more strongly with adverse cardiovascular events than does daytime blood pressure. The BedMed trial evaluates whether bedtime antihypertensive administration, as compared with conventional morning use, reduces major adverse cardiovascular events. METHODS AND ANALYSIS: DesignProspective randomised, open-label, blinded end-point trial.ParticipantsHypertensive primary care patients using blood pressure lowering medication and free from glaucoma.SettingCommunity primary care providers in 5 Canadian provinces (British Columbia, Alberta, Saskatchewan, Manitoba and Ontario) are mailing invitations to their eligible patients. Social media campaigns (Google, Facebook) are additionally running in the same provinces.InterventionConsenting participants are allocated via central randomisation to bedtime vs morning use of all antihypertensives.Follow-up(1) Telephone or email questionnaire at 1 week, 6 weeks, 6 months and every 6 months thereafter, and (2) accessing linked governmental healthcare databases tracking hospital and community medical services.Primary outcomeComposite of all-cause death, or hospitalisation for myocardial infarction/acute-coronary syndrome, stroke or congestive heart failure.Secondary outcomesEach primary outcome element on its own, all-cause hospitalisation or emergency department visit, long-term care admission, non-vertebral fracture, new glaucoma diagnosis, 18-month cognitive decline from baseline (via Short Blessed Test).Select other outcomesSelf-reported nocturia burden at 6 weeks and 6 months (no, minor or major burden), 1-year self-reported overall health score (EQ-5D-5L), self-reported falls, total cost of care (acute and community over study duration) and mean sleep-time systolic blood pressure after 6 months (via 24-hour monitor in a subset of 302 sequential participants).Primary outcome analysisCox proportional hazards survival analysis.Sample sizeThe trial will continue until a projected 254 primary outcome events have occurred.Current statusEnrolment ongoing (3227 randomised to date). ETHICS AND DISSEMINATION: BedMed has ethics approval from six research ethics review boards and will publish results in a peer-reviewed journal. TRIAL REGISTRATION NUMBER: NCT02990663.

Non-negative matrix factorization temporal topic models and clinical text data identify COVID-19 pandemic effects on primary healthcare and community health in Toronto, Canada.

OBJECTIVE: To demonstrate how non-negative matrix factorization can be used to learn a temporal topic model over a large collection of primary care clinical notes, characterizing diverse COVID-19 pandemic effects on the physical/mental/social health of residents of Toronto, Canada. MATERIALS AND METHODS: The study employs a retrospective open cohort design, consisting of 382,666 primary care progress notes from 44,828 patients, 54 physicians, and 12 clinics collected 01/01/2017 through 31/12/2020. Non-negative matrix factorization uncovers a meaningful latent topical structure permeating the corpus of primary care notes. The learned latent topical basis is transformed into a multivariate time series data structure. Time series methods and plots showcase the evolution/dynamics of learned topics over the study period and allow the identification of COVID-19 pandemic effects. We perform several post-hoc checks of model robustness to increase trust that descriptive/unsupervised inferences are stable over hyper-parameter configurations and/or data perturbations. RESULTS: Temporal topic modelling uncovers a myriad of pandemic-related effects from the expressive clinical text data. In terms of direct effects on patient-health, topics encoding respiratory disease symptoms display altered dynamics during the pandemic year. Further, the pandemic was associated with a multitude of indirect patient-level effects on topical domains representing mental health, sleep, social and familial dynamics, measurement of vitals/labs, uptake of prevention/screening maneuvers, and referrals to medical specialists. Finally, topic models capture changes in primary care practice patterns resulting from the pandemic, including changes in EMR documentation strategies and the uptake of telemedicine. CONCLUSION: Temporal topic modelling applied to a large corpus of rich primary care clinical text data, can identify a meaningful topical/thematic summarization which can provide policymakers and public health stakeholders a passive, cost-effective, technology for understanding holistic impacts of the COVID-19 pandemic on the primary healthcare system and community/public-health.

Association between new-onset anosmia and positive SARS-CoV-2 tests among people accessing outpatient testing in Toronto, Ontario: a retrospective cross-sectional study.

BACKGROUND: Reports have suggested that anosmia is strongly associated with SARS-CoV-2 infection, but patients were often asked about this symptom after their diagnosis. This study assessed associations between prospectively reported anosmia and other symptoms related to SARS-CoV-2 infection, and SARS-CoV-2 positivity in community testing centres in Toronto, Ontario. METHODS: We conducted a retrospective cross-sectional study in which data were collected from 2 COVID-19 assessment centres affiliated with 2 hospitals in Toronto, Ontario, from Apr. 5 to Sept. 30, 2020. We included symptomatic profiles of all people who underwent a SARS-CoV-2 test at either clinic within the study period. We used generalized estimating equations to account for repeat visits and to assess associations between anosmia and other symptoms and SARS-CoV-2 positivity. RESULTS: A total of 83 443 SARS-CoV-2 tests were conducted across the 2 sites for 72 692 participants during the study period. Of all tests, 1640 (2.0%) were positive; 837 (51.0%) of people who tested positive were asymptomatic. The adjusted odds ratio for the association between anosmia and test positivity was 5.29 (95% confidence interval [CI] 4.50-6.22), with sensitivity of 0.138 (95% CI 0.121-0.154), specificity of 0.980 (95% CI 0.979-0.981), a positive predictive value of 0.120 (95% CI 0.106-0.135) and a negative predictive value of 0.983 (95% CI 0.982-0.984). INTERPRETATION: Anosmia had high specificity and a positive predictive value of 12% for SARS-CoV-2 infection in this community population with low prevalence of SARS-CoV-2 positivity. The presence of anosmia should increase clinical suspicion of SARS-CoV-2 infection, and our findings suggest that people presenting with this symptom should be tested.

Effectiveness of an eHealth self-management tool for older adults with multimorbidity (KeepWell): protocol for a hybrid effectiveness-implementation randomised controlled trial.

INTRODUCTION: In response to the burden of chronic disease among older adults, different chronic disease self-management tools have been created to optimise disease management. However, these seldom consider all aspects of disease management are not usually developed specifically for seniors or created for sustained use and are primarily focused on a single disease. We created an eHealth self-management application called 'KeepWell' that supports seniors with complex care needs in their homes. It incorporates the care for two or more chronic conditions from among the most prevalent high-burden chronic diseases. METHODS AND ANALYSIS: We will evaluate the effectiveness, cost and uptake of KeepWell in a 6-month, pragmatic, hybrid effectiveness-implementation randomised controlled trial. Older adults age ≥65 years with one or more chronic conditions who are English speaking are able to consent and have access to a computer or tablet device, internet and an email address will be eligible. All consenting participants will be randomly assigned to KeepWell or control. The allocation sequence will be determined using a random number generator.Primary outcome is perceived self-efficacy at 6 months. Secondary outcomes include quality of life, health background/status, lifestyle (nutrition, physical activity, caffeine, alcohol, smoking and bladder health), social engagement and connections, eHealth literacy; all collected via a Health Risk Questionnaire embedded within KeepWell (intervention) or a survey platform (control). Implementation outcomes will include reach, effectiveness, adoption, fidelity, implementation cost and sustainability. ETHICS AND DISSEMINATION: Ethics approval has been received from the North York General Hospital Research and Ethics Board. The study is funded by the Canadian Institutes of Health Research and the Ontario Ministry of Health. We will work with our team to develop a dissemination strategy which will include publications, presentations, plain language summaries and an end-of-grant meeting. TRIAL REGISTRATION NUMBER: NCT04437238.