Explore the vast range of titles available.

Background Housing and income are important social determinants of health (SDoH). Primary care providers often do not have information about these determinants, which could be used to support equitable health system planning and care delivery. The aim of this study was to use primary care electronic medical record (EMR) data to test two approaches (machine learning and regular expression searches) to obtain information about patients’ housing instability and low income status. Methods We used de-identified EMR data from the St. Michael’s Hospital Academic Family Health Team (Toronto, Ontario, Canada). A Health Equity Questionnaire is also routinely distributed to patients and includes questions about income and housing status; this formed the reference standard. First, a regular expression (REGEX) classifier was created using key text terms and codes; the second approach used supervised machine learning models (XGBoost). Discrimination and calibration metrics were calculated as compared to the patient-reported responses. Results 11,794 eligible patients were included in the housing cohort and 10,454 were in the income cohort. Overall, both approaches had poor sensitivity for determining both housing instability (XGBoost: 3.1%, REGEX: 29.0%) and low income status (XGBoost: 41.7%, REGEX: 17.6%). Positive predictive value (PPV) was satisfactory for the machine learning approach (83.3% for housing, 72.9% for income). Conclusion While the machine learning approach demonstrated reasonable PPV, the overall metrics were poor and unlikely to be useful in a clinical setting for identifying patients with housing or economic needs. More robust analysis could be explored, but continued patient-captured SDoH information is necessary.

Background Hypertension is a common chronic condition affecting nearly a quarter of Canadians. Hypertension surveillance in Canada typically relies on administrative data and/or national surveys. Routinely-captured data from primary care electronic medical records (EMRs) are a complementary source for chronic disease surveillance, with longitudinal patient-level details such as sociodemographics, blood pressure, weight, prescribed medications, and behavioural risk factors. As EMR data are generated from patient care and administrative tasks, assessing data quality is essential before using for secondary purposes. This study evaluated the quality of primary care EMR data from one province in Canada within the context of hypertension surveillance. Methods We conducted a cross-sectional, descriptive study using primary care EMR data collected by two practice-based research networks in Alberta, Canada. There were 48,377 adults identified with hypertension from 53 clinics as of June 2018. Summary statistics were used to examine the quality of data elements considered relevant for hypertension surveillance. Results Patient year of birth and sex were complete, but other sociodemographic information (ethnicity, occupation, education) was largely incomplete and highly variable. Height, weight, body mass index and blood pressure were complete for most patients (over 90%), but a small proportion of outlying values indicate data inaccuracies were present. Most patients had a relevant laboratory test present (e.g. blood glucose/glycated hemoglobin, lipid profile), though a very small proportion of values were outside a biologically plausible range. Details of prescribed antihypertensive medication, such as start date, strength, dose, frequency, were mostly complete. Nearly 80% of patients had a smoking status recorded, though only 66% had useful information (i.e. categorized as current, past, or never), and less than half had their alcohol use described; information related to amount, frequency or duration was not available. Conclusions Blood pressure and prescribed medications in primary care EMR data demonstrated good completeness and plausibility, and contribute valuable information for hypertension epidemiology and surveillance. The use of other clinical, laboratory, and sociodemographic variables should be used carefully due to variable completeness and suspected data errors. Additional strategies to improve these data at the point of entry and after data extraction (e.g. statistical methods) are required.

General practice electronic health records (EHRs) contain a wealth of patient information. However, these data are collected for clinical purposes. Hence, questions remain around the suitability of using these data for other purposes, including epidemiological research, developing and validating clinical prediction models, conducting audits, and informing policy. This study aimed to compare the quality of osteoarthritis-related data in Australian and Canadian general practice EHRs for externally validating a clinical prediction model for total knee replacement surgery. A data quality assessment was conducted on 201,462 patient general practice EHRs from Australia provided by National Prescribing Service MedicineWise, and 92,425 from Canada provided by the Canadian Primary Care Sentinel Surveillance Network. Completeness, plausibility, and external validity of data elements relevant to osteoarthritis were assessed. Completeness and plausibility were evaluated using counts and proportions. For external validity, prevalence was estimated using proportions, and knee replacement summarized as a rate per 100,000 population. There were minimal incomplete and implausible data fields for age and sex (<1%), geographic location (<5%), and commonly cooccurring comorbidities (<10%) in both datasets. However, weight, height, BMI, and Canadian Index of Multiple Deprivation contained >50% missing data. The recording of osteoarthritis by age and sex in both datasets were similar to national estimates, except for patients aged >80 years (Australia: 16.6%, 95% CI 16%-17.3% vs 13.1%, 95% CI 11.2%-15.4%; Canada: 36.7%, 95% CI 36.1%-37.2% vs 50.8%, 95% CI 50.7%-50.9%). Total knee replacement rates were substantially lower in both EHR datasets compared with national estimates (Australia: 72 vs 218 per 100,000; Canada: 0.84 vs 200 per 100,000). Age, sex, geographic location, commonly cooccurring comorbidities, and prescribing of osteoarthritis medications in Australian and Canadian general practice EHRs are suitable for use in clinical prediction model validation studies. However, BMI and the Canadian Index of Multiple Deprivation are unfit for such use due to large proportions of missing data. Rates of total knee replacement surgery were substantially underreported and should not be used for prediction model validation. Better harmonization of patient data across primary and tertiary care is required to improve the suitability of these data. In the meantime, data linkage with national registries and other health datasets may overcome some of the data quality challenges in general practice EHRs.

Data on the social determinants of health could be used to improve care, support quality improvement initiatives, and track progress toward health equity. However, this data collection is not widespread. Artificial intelligence (AI), specifically natural language processing and machine learning, could be used to derive social determinants of health data from electronic medical records. This could reduce the time and resources required to obtain social determinants of health data. This study aimed to understand perspectives of a diverse sample of Canadians on the use of AI to derive social determinants of health information from electronic medical record data, including benefits and concerns. Using a qualitative description approach, in-depth interviews were conducted with 195 participants purposefully recruited from Ontario, Newfoundland and Labrador, Manitoba, and Saskatchewan. Transcripts were analyzed using an inductive and deductive content analysis. A total of 4 themes were identified. First, AI was described as the inevitable future, facilitating more efficient, accessible social determinants of health information and use in primary care. Second, participants expressed concerns about potential health care harms and a distrust in AI and public systems. Third, some participants indicated that AI could lead to a loss of the human touch in health care, emphasizing a preference for strong relationships with providers and individualized care. Fourth, participants described the critical importance of consent and the need for strong safeguards to protect patient data and trust. These findings provide important considerations for the use of AI in health care, and particularly when health care administrators and decision makers seek to derive social determinants of health data.

Background The use of general practice electronic health records (EHRs) for research purposes is in its infancy in Australia. Given these data were collected for clinical purposes, questions remain around data quality and whether these data are suitable for use in prediction model development. In this study we assess the quality of data recorded in 201,462 patient EHRs from 483 Australian general practices to determine its usefulness in the development of a clinical prediction model for total knee replacement (TKR) surgery in patients with osteoarthritis (OA). Methods Variables to be used in model development were assessed for completeness and plausibility. Accuracy for the outcome and competing risk were assessed through record level linkage with two gold standard national registries, Australian Orthopaedic Association National Joint Replacement Registry (AOANJRR) and National Death Index (NDI). The validity of the EHR data was tested using participant characteristics from the 2014–15 Australian National Health Survey (NHS). Results There were substantial missing data for body mass index and weight gain between early adulthood and middle age. TKR and death were recorded with good accuracy, however, year of TKR, year of death and side of TKR were poorly recorded. Patient characteristics recorded in the EHR were comparable to participant characteristics from the NHS, except for OA medication and metastatic solid tumour. Conclusions In this study, data relating to the outcome, competing risk and two predictors were unfit for prediction model development. This study highlights the need for more accurate and complete recording of patient data within EHRs if these data are to be used to develop clinical prediction models. Data linkage with other gold standard data sets/registries may in the meantime help overcome some of the current data quality challenges in general practice EHRs when developing prediction models.

Background Primary care electronic medical record (EMR) data are emerging as a useful source for secondary uses, such as disease surveillance, health outcomes research, and practice improvement. These data capture clinical details about patients’ health status, as well as behavioural risk factors, such as smoking. While the importance of documenting smoking status in a healthcare setting is recognized, the quality of smoking data captured in EMRs is variable. This study was designed to test methods aimed at improving the quality of patient smoking information in a primary care EMR database. Methods EMR data from community primary care settings extracted by two regional practice-based research networks in Alberta, Canada were used. Patients with at least one encounter in the previous 2 years (2016–2018) and having hypertension according to a validated definition were included ( n  = 48,377). Multiple imputation was tested under two different assumptions for missing data (smoking status is missing at random and missing not-at-random). A third method tested a novel pattern matching algorithm developed to augment smoking information in the primary care EMR database. External validity was examined by comparing the proportions of smoking categories generated in each method with a general population survey. Results Among those with hypertension, 40.8% ( n  = 19,743) had either no smoking information recorded or it was not interpretable and considered missing. Those with missing smoking data differed statistically by demographics, clinical features, and type of EMR system used in the clinic. Both multiple imputation methods produced fully complete smoking status information, with the proportion of current smokers estimated at 25.3% (data missing at random) and 12.5% (data missing not-at-random). The pattern-matching algorithm classified 18.2% of patients as current smokers, similar to the population-based survey (18.9%), but still resulted in missing smoking information for 23.6% of patients. The algorithm was estimated to be 93.8% accurate overall, but varied by smoking status category. Conclusion Multiple imputation and algorithmic pattern-matching can be used to improve EMR data post-extraction but the recommended method depends on the purpose of secondary use (e.g. practice improvement or epidemiological analyses).

Background Menopause is a normal transition in a woman’s life. For some women, it is a stage without significant difficulties; for others, menopause symptoms can severely affect their quality of life. This study developed and validated a case definition for problematic menopause using Canadian primary care electronic medical records, which is an essential step in examining the condition and improving quality of care. Methods We used data from the Canadian Primary Care Sentinel Surveillance Network including billing and diagnostic codes, diagnostic free-text, problem list entries, medications, and referrals. These data formed the basis of an expert-reviewed reference standard data set and contained the features that were used to train a machine learning model based on classification and regression trees. An ad hoc feature importance measure coupled with recursive feature elimination and clustering were applied to reduce our initial 86,000 element feature set to a few tens of the most relevant features in the data, while class balancing was accomplished with random under- and over-sampling. The final case definition was generated from the tree-based machine learning model output combined with a feature importance algorithm. Two independent samples were used: one for training / testing the machine learning algorithm and the other for case definition validation. Results We randomly selected 2,776 women aged 45–60 for this analysis and created a case definition, consisting of two occurrences within 24 months of International Classification of Diseases, Ninth Revision, Clinical Modification code 627 (or any sub-codes) OR one occurrence of Anatomical Therapeutic Chemical classification code G03CA (or any sub-codes) within the patient chart, that was highly effective at detecting problematic menopause cases. This definition produced a sensitivity of 81.5% (95% CI: 76.3-85.9%), specificity of 93.5% (91.9-94.8%), positive predictive value of 73.8% (68.3-78.6%), and negative predictive value of 95.7% (94.4-96.8%). Conclusion Our case definition for problematic menopause demonstrated high validity metrics and so is expected to be useful for epidemiological study and surveillance. This case definition will enable future studies exploring the management of menopause in primary care settings.

Objective Documenting cannabis use is important for patient care, but no formal requirements for consistent reporting exist in primary care. The objective of this study was to understand how cannabis use is documented in primary care electronic medical record (EMR) data. Results This was a cross-sectional study using de-identified EMR data from over 398,000 patients and 333 primary care providers in Alberta, Canada. An automated pattern-matching algorithm was developed to identify text and ICD-9 diagnostic codes indicating cannabis use in the EMR. There was a total of 11,724 records indicating cannabis use from 4652 patients, representing approximately 1.2% of the patient sample. Commonly used terms and ICD-9 codes included cannabis , marijuana/marihuana, THC, 304.3 and 305.2. Nabilone was the most frequently prescribed cannabinoid medication. Slightly more males and those with a chronic condition had cannabis use recorded more often. Overall, very few patients have cannabis use recorded in primary care EMR data and this is not captured in a systematic way. We propose several strategies to improve the documentation of cannabis use to facilitate more effective clinical care, research, and surveillance.

ObjectiveTo describe the process for linking electronic medical record (EMR) and administrative data in Alberta and examine the advantages and limitations of utilising linked data for hypertension surveillance.MethodsDe-identified EMR data from 323 primary care providers contributing to the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) in Alberta were used. Mapping files from each contributing provider were generated from their EMR to facilitate linkage to administrative data within the provincial health data warehouse. Deterministic linkage was conducted using valid personal healthcare number (PHN) with age and/or sex. Characteristics of patients and providers in the linked cohort were compared with population-level sources. Criteria used to define hypertension in both sources were examined.ResultsData were successfully linked for 6307 hypertensive patients (96.2% of eligible patients) from 49 contributing providers. Non-linkages from invalid PHN (n=246) occurred more for deceased patients and those with fewer primary care encounters, with differences due to type of EMR and patient EMR status. The linked cohort had more patients who were female, >60 years and residing in rural areas compared to the provincial healthcare registry. Family physicians were more often female and medically trained in Canada compared to all physicians in Alberta. Most patients (>97%) had ≥1 record in the registry, pharmacy, emergency/ambulatory care and claims databases; 44.3% had ≥1 record in the hospital discharge database.ConclusionEMR-administrative data linkage has the potential to enhance hypertension surveillance. The current linkage process in Alberta is limited and subject to selection bias. Processes to address these deficiencies are under way.