RESUMO
OBJECTIVE: To understand the perspectives of primary care clinicians and health system leaders on the use of artificial intelligence (AI) to derive information about patients' social determinants of health. DESIGN: Qualitative study. SETTING: Ontario, Canada. METHODS: Semistructured, 30-minute virtual interviews were conducted with eligible participants across Ontario wherein they were asked about their perceptions of using AI to derive social data for patients. A descriptive content analysis was used to elicit themes from the data. MAIN FINDINGS: A total of 12 interviews were conducted with 7 family physicians, 3 clinical team members of various health professions, and 2 health system leaders. Five main themes described the current state of social determinants of health information, perceived benefits of and concerns with using AI to derive social data, how participants would want to see and use AI-derived social data, and suggestions for ethical principles that should underpin the development of this AI tool. CONCLUSION: Most participants were enthusiastic about the possibility of using AI to derive social data for patients in primary care but noted concerns that should be addressed first. These findings can guide the development of AI-based tools for use in primary care settings.
Assuntos
Inteligência Artificial , Atenção Primária à Saúde , Pesquisa Qualitativa , Determinantes Sociais da Saúde , Humanos , Ontário , Masculino , Feminino , Atitude do Pessoal de Saúde , Adulto , Pessoa de Meia-Idade , Entrevistas como AssuntoRESUMO
PURPOSE: Information about social determinants of health (SDOH) is essential for primary care clinicians in the delivery of equitable, comprehensive care, as well as for program planning and resource allocation. SDOH are rarely captured consistently in clinical settings, however. Artificial intelligence (AI) could potentially fill these data gaps, but it needs to be designed collaboratively and thoughtfully. We report on a codesign process with primary care clinicians to understand how an AI tool could be developed, implemented, and used in practice. METHODS: We conducted semistructured, 50-minute workshops with a large urban family health team in Toronto, Ontario, Canada asking their feedback on a proposed AI-based tool used to derive patient SDOH from electronic health record data. An inductive thematic analysis was used to describe participants' perspectives regarding the implementation and use of the proposed tool. RESULTS: Fifteen participants contributed across 4 workshops. Most patient SDOH information was not available or was difficult to find in their electronic health record. Discussions focused on 3 areas related to the implementation and use of an AI tool to derive social data: people, process, and technology. Participants recommended starting with 1 or 2 social determinants (income and housing were suggested as priorities) and emphasized the need for adequate resources, staff, and training materials. They noted many challenges, including how to discuss the use of AI with patients and how to confirm their social needs identified by the AI tool. CONCLUSIONS: Our codesign experience provides guidance from end users on the appropriate and meaningful design and implementation of an AI-based tool for social data in primary care.
Assuntos
Inteligência Artificial , Registros Eletrônicos de Saúde , Atenção Primária à Saúde , Determinantes Sociais da Saúde , Humanos , Ontário , Pesquisa QualitativaRESUMO
BACKGROUND: Most antibiotics dispensed by community pharmacies in Canada are prescribed by family physicians, but using the prescribing information contained within primary care electronic medical records (EMRs) for secondary purposes can be challenging owing to variable data quality. We used antibiotic medications as an exemplar to validate a machine-learning approach for cleaning and coding medication data in a pan-Canadian primary care EMR database. METHODS: The Canadian Primary Care Sentinel Surveillance Network database contained an estimated 42 million medication records, which we mapped to an Anatomic Therapeutic Chemical (ATC) code by applying a semisupervised classification model developed using reference standard labels derived from the Health Canada Drug Product Database. We validated the resulting ATC codes in a subset of antibiotic records (16 119 unique strings) to determine whether the algorithm correctly classified the medication according to manual review of the original medication record. RESULTS: In the antibiotic subset, the algorithm showed high validity (sensitivity 99.5%, specificity 92.4%, positive predictive value 98.6%, negative predictive value 97.0%) in classifying whether the medication was an antibiotic. INTERPRETATION: Our machine-learning algorithm classified unstructured antibiotic medication data from primary care with a high degree of accuracy. Access to cleaned EMR data can support important secondary uses, including community-based antibiotic prescribing surveillance and practice improvement.
RESUMO
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.
Assuntos
Registros Eletrônicos de Saúde , Qualidade de Vida , Humanos , Feminino , Canadá , Algoritmos , Menopausa , Atenção Primária à SaúdeRESUMO
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.
Assuntos
Cannabis , Masculino , Humanos , Registros Eletrônicos de Saúde , Alberta/epidemiologia , Estudos Transversais , Atenção Primária à SaúdeRESUMO
OBJECTIVE: To characterize transitions to acute and residential care and identify variables associated with specific transitions among community-based persons living with dementia (PLWD). DESIGN: Retrospective cohort study using primary care electronic medical record data linked with health administrative data. SETTING: Alberta. PARTICIPANTS: Adults aged 65 years or older living in the community who had been diagnosed with dementia and who saw a Canadian Primary Care Sentinel Surveillance Network contributor between January 1, 2013, and February 28, 2015. MAIN OUTCOME MEASURES: All emergency department visits, hospitalizations, residential care (supportive living and long-term care) admissions, and deaths within a 2-year follow-up period. RESULTS: In total, 576 PLWD were identified who had a mean (SD) age of 80.4 (7.7) years; 55% were female. In 2 years, 423 (73.4%) had at least 1 transition and, of these, 111 (26.2%) had 6 or more. Emergency department visits, including multiple visits, were common (71.4% had ≥1, 12.1% had ≥4). Of those hospitalized (43.8%), nearly all were admitted from the emergency department; the average (SD) length of stay was 23.6 (35.8) days, and 32.9% had at least 1 alternate level of care day. In total, 19.3% entered residential care, most admitted from hospital. Those admitted to hospital and those admitted to residential care were older and had greater historical health system use, including home care. One-quarter of the sample did not have any transitions (or die) during follow-up; they were typically younger and had limited historical health system use. CONCLUSION: Older PLWD experienced frequent, and frequently compound, transitions that have implications for them, their family members, and the health system. There was also a large proportion without transitions suggesting that appropriate supports enable PLWD to do well in their own communities. The identification of PLWD who are at risk of or who make frequent transitions may allow for more proactive implementation of community-based supports and smoother transitions to residential care.
Assuntos
Demência , Serviços de Assistência Domiciliar , Adulto , Humanos , Feminino , Idoso , Idoso de 80 Anos ou mais , Masculino , Estudos Retrospectivos , Alberta , HospitalizaçãoRESUMO
The International Classification of Diseases, Ninth Revision (ICD-9) was released in the 1970s and adopted in Canada for physician billing claims in 1979 (CIHI n.d.b.; WHO & International Conference for the Ninth Revision of the International Classification of Diseases 1977). ICD-9 is no longer adequate for representing our modern healthcare environment and patient needs. We summarize the findings from a small survey of ICD-9 users across Canada - such as family physicians, researchers and decision makers - who describe the limitations of ICD-9 and the features that they would desire in a new or updated classification system.
Assuntos
Classificação Internacional de Doenças , Médicos , Canadá , Humanos , Inquéritos e QuestionáriosRESUMO
OBJECTIVES: Glucagon-like peptide-1 receptor agonists (GLP-1 RA) and sodium-glucose cotransporter-2 inhibitors (SGLT2i) have shown cardiorenal benefits independent of their glucose-lowering effects among persons living with type 2 diabetes mellitus (T2DM). In this study, we describe the proportion of persons with T2DM eligible to receive and currently receiving these agents based on their risk criteria for cardiorenal events. METHODS: This study was a cross-sectional analysis of primary care electronic medical records, in southern Alberta, of persons with T2DM who had at least 1 encounter with their primary care provider between December 31, 2018, to December 31, 2020. A descriptive and multivariate logistic regression analysis was conducted to examine clinical and demographic determinants of being prescribed one of the new treatments. RESULTS: Our study sample included 11,939 persons living with T2DM, among whom 66.3% had a cardiorenal indication for SGLT2i or GLP-1 RA use. In the secondary and primary prevention subsamples, 19.4% and 16.6% of persons were prescribed SGLT2i or GLP-1 RA, respectively, compared with 20.0% of those with no specific cardiorenal indication. Several person-level characteristics, such as age (odds ratio [OR], 0.96; 95% confidence interval [CI], 0.96 to 0.97), male sex (OR, 1.37; 95% CI, 1.21 to 1.55) and glycated hemoglobin (OR, 1.29; 95% CI, 1.24 to 1.34), were associated with being prescribed SGLT2i or GLP-1 RA. CONCLUSIONS: Low rates of SGLT2i or GLP-1 RA use and minimal differences between high-risk and no cardiorenal indication subsamples suggest the presence of barriers to prescribing these medications in a primary care setting. Action to highlight the indications for, and improve access to agents with, cardiorenal benefits will be required to achieve better outcomes for people with T2DM in primary care.
Assuntos
Diabetes Mellitus Tipo 2 , Inibidores do Transportador 2 de Sódio-Glicose , Adulto , Estudos Transversais , Diabetes Mellitus Tipo 2/complicações , Diabetes Mellitus Tipo 2/tratamento farmacológico , Diabetes Mellitus Tipo 2/epidemiologia , Peptídeo 1 Semelhante ao Glucagon/uso terapêutico , Glucose , Humanos , Hipoglicemiantes/farmacologia , Hipoglicemiantes/uso terapêutico , Masculino , Atenção Primária à Saúde , Inibidores do Transportador 2 de Sódio-Glicose/farmacologia , Inibidores do Transportador 2 de Sódio-Glicose/uso terapêuticoRESUMO
BACKGROUND: Cardiovascular disease (CVD) is a major cause of morbidity and mortality in Canada. Assessment and management of CVD risk is essential in reducing disease burden. This includes both clinical risk factors and socioeconomic factors, though few studies report on socioeconomic status in relation to CVD risk and treatment. The primary objective of this study was to estimate the cardiovascular risk of patients attending primary care practices across Canada; secondly, to evaluate concordance with care indicators suggested by current clinical practice guidelines for statin prescribing according to patients' cardiovascular risk and socioeconomic status. METHODS: This cross-sectional observational study used the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) database, which is comprised of clinical data from primary care electronic medical records. Patients aged 35-75y with at least one visit to their primary care provider between 2012 and 2016 were included. Patients were assigned to a CVD risk category (high, medium, low) and a deprivation quintile was calculated for those with full postal code available. Descriptive analyses were used to determine the proportion of patients in each risk category. Logistic regression was used to evaluate the consistency of statin prescribing according to national clinical guidelines by risk category and deprivation quintile. RESULTS: A total of 324,526 patients were included. Of those, 116,947 (36%) of patients were assigned to a high CVD risk category, primarily older adults, males, and those with co-morbidities. There were statistically significant differences between least (quintile 1) and most (quintile 5) deprived socioeconomic quintiles, with those at high CVD risk disproportionately in Q5 (odds ratio 1.4). Overall, 48% of high-risk patients had at least one statin prescription in their record. Patients in the lower socioeconomic groups had a higher risk of statin treatment which deviated from clinical guidelines. CONCLUSIONS: Primary care patients who are at high CVD risk are more often male, older, have more co-morbidities and be assigned to more deprived SES quintiles, compared to those at low CVD risk. Additionally, patients who experience more challenging socioeconomic situations may be less likely to receive CVD treatment that is consistent with care guidelines.
Assuntos
Doenças Cardiovasculares , Inibidores de Hidroximetilglutaril-CoA Redutases , Idoso , Canadá/epidemiologia , Doenças Cardiovasculares/tratamento farmacológico , Estudos Transversais , Fatores de Risco de Doenças Cardíacas , Humanos , Inibidores de Hidroximetilglutaril-CoA Redutases/uso terapêutico , Masculino , Atenção Primária à Saúde , Fatores de Risco , Vigilância de Evento SentinelaRESUMO
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.
Assuntos
Confiabilidade dos Dados , Registros Eletrônicos de Saúde , Adulto , Austrália , Medicina de Família e Comunidade , Humanos , Pessoa de Meia-Idade , Modelos Estatísticos , PrognósticoRESUMO
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.
Assuntos
Registros Eletrônicos de Saúde , Hipertensão , Adulto , Alberta/epidemiologia , Estudos Transversais , Confiabilidade dos Dados , Humanos , Hipertensão/tratamento farmacológico , Hipertensão/epidemiologia , Atenção Primária à SaúdeRESUMO
OBJECTIVE: To 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. METHODS: De-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. RESULTS: Data 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. CONCLUSION: EMR-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.
Assuntos
Demandas Administrativas em Assistência à Saúde/estatística & dados numéricos , Registros Eletrônicos de Saúde/estatística & dados numéricos , Hipertensão/diagnóstico , Armazenamento e Recuperação da Informação , Atenção Primária à Saúde , Vigilância de Evento Sentinela , Idoso , Alberta , Estudos de Coortes , Bases de Dados Factuais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Médicos de FamíliaRESUMO
BACKGROUND: To date, there has been no validated method to identify cases of pelvic floor disorders in primary care electronic medical record (EMR) data. We aimed to develop and validate symptom-based case definitions for urinary incontinence, fecal incontinence and pelvic organ prolapse in women, for use in primary care epidemiologic or clinical research. METHODS: Our retrospective study used EMR data from the Southern Alberta Primary Care Research Network (SAPCReN) and the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) in southern Alberta. Trained researchers remotely reviewed a random sample of EMR charts of women aged 18 years or older from 6 rural and urban clinics to validate case definitions for urinary incontinence, fecal incontinence and pelvic organ prolapse. We calculated sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV), and estimated SAPCReN prevalence as appropriate. RESULTS: Charts of 900 women were included. Sensitivity was 81.9% (95% confidence interval [CI] 75.1-87.2) for urinary incontinence, 61.2% (95% CI 46.2-74.5) for fecal incontinence, and 51.8% (95% CI 40.6-62.8) for pelvic organ prolapse. Corresponding specificity values were 71.9% (95% CI 68.4-75.1), 99.2% (95% CI 98.2-99.6) and 98.8% (95% CI 97.7-99.4), PPVs 40.6% (95% CI 35.4-46.0), 81.1% (95% CI 64.3-91.4) and 81.1% (95% CI 67.6-90.1), and NPVs 94.4% (95% CI 92.1-96.1), 97.8% (95% CI 96.5-98.6) and 95.3% (95% CI 93.6-96.6). The SAPCReN-observed prevalence for urinary incontinence was 29.7% (95% CI 29.3-30.0), but the adjusted prevalence was 2.97%. INTERPRETATION: The case definition for urinary incontinence met our standard for validity (sensitivity and specificity > 70%), and the case definitions for fecal incontinence and pelvic organ prolapse had PPVs greater than 80%. The urinary incontinence definition may be used in epidemiologic research, and those for fecal incontinence and pelvic organ prolapse may be used in quality-improvement studies or creation of disease registries. Our symptom-based case definitions could also be adapted for research in other EMR settings.
Assuntos
Distúrbios do Assoalho Pélvico/epidemiologia , Atenção Primária à Saúde , Encaminhamento e Consulta , Serviços de Saúde da Mulher , Alberta/epidemiologia , Registros Eletrônicos de Saúde , Feminino , Pesquisas sobre Atenção à Saúde , Humanos , Distúrbios do Assoalho Pélvico/diagnóstico , Distúrbios do Assoalho Pélvico/terapia , Reprodutibilidade dos Testes , Estudos RetrospectivosRESUMO
OBJECTIVE: To validate a case definition for speech and language disorders in community-dwelling older adults and to determine the prevalence of speech and language disorders in a primary care population. DESIGN: This is a combined case definition validation and cross-sectional prevalence study. Chart review was considered the reference standard and was used to estimate prevalence. This study used de-identified electronic medical record data from participating SAPCReN-CPCSSN (Southern Alberta Primary Care Research Network-Canadian Primary Care Sentinel Surveillance Network) primary care clinics. SETTING: Southern Alberta. PARTICIPANTS: Men and women aged 55 years and older who had visited a SAPCReN-CPCSSN physician or nurse practitioner at least once in the 2 years before the beginning of the study. MAIN OUTCOME MEASURES: Validation analysis included estimation of sensitivity, specificity, positive predictive value, and negative predictive value. Prevalence was the other main outcome measure. RESULTS: The prevalence of speech and language disorders within the sample of 1384 patients was 1.2%. The case definition had a favourable specificity (99.9%, 95% CI 99.6% to 100.0%), positive predictive value (75.6%, 95% CI 25.4% to 96.6%), and negative predictive value (99.0%, 95% CI 98.8% to 99.2%). Sensitivity was not sufficient for validity (18.8%, 95% CI 4.05% to 45.6%). CONCLUSION: The case definition did not meet an acceptable standard for validity and thus cannot be used for future epidemiologic research. However, owing to the case definition's high positive predictive value, it might be useful for clinical purposes and for cohort studies. Finally, while the case definition did not prove valid, this study has provided a conservative estimate of prevalence (1.2%) given the case definition's high specificity.
Assuntos
Atenção Primária à Saúde , Distúrbios da Fala/epidemiologia , Idoso , Idoso de 80 Anos ou mais , Alberta/epidemiologia , Estudos Transversais , Registros Eletrônicos de Saúde , Feminino , Humanos , Vida Independente , Masculino , Pessoa de Meia-Idade , Prevalência , Estudos Retrospectivos , Vigilância de Evento SentinelaRESUMO
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).
Assuntos
Algoritmos , Coleta de Dados/métodos , Bases de Dados Factuais/normas , Registros Eletrônicos de Saúde/estatística & dados numéricos , Atenção Primária à Saúde/estatística & dados numéricos , Fumar/epidemiologia , Idoso , Alberta , Estudos de Coortes , Feminino , Humanos , Hipertensão/epidemiologia , Masculino , Pessoa de Meia-IdadeRESUMO
BACKGROUND AND OBJECTIVES: The landscape of antimicrobial resistance (AMR) surveillance is changing rapidly. The primary objective of this study was to assess the benefit of linking population-based infection prevention and control surveillance data on methicillin-resistant Staphylococcus aureus (MRSA) to hospital discharge abstract data (DAD). We assessed the value of this novel data linkage for the characterization of hospital-acquired (HA) and community-acquired MRSA (CA-MRSA) cases. METHODS: Incident inpatient MRSA surveillance data for all adults (≥18 years) from 4 acute-care facilities in Calgary, Alberta, between April 1, 2011, and March 31, 2017, were linked to DAD. Personal health number (PHN) and gender were used to identify specific individuals, and specimen collection time-points were used to identify specific hospitalization records. A third common variable on admission date between these databases was used to validate the linkage process. Descriptive statistics were used to characterize HA-MRSA and CA-MRSA cases identified through the linkage process. RESULTS: A total of 2,430 surveillance records (94.6%) were successfully linked to the correct hospitalization period. By linking surveillance and administrative data, we were able to identify key differences between patients with HA- and CA-MRSA. These differences are consistent with previously reported findings in the literature. Data linkage to DAD may be a novel tool to enhance and augment the details of base surveillance data. CONCLUSION AND RECOMMENDATIONS: This is the first Canadian study linking a frontline healthcare-associated infection AMR surveillance database to an administrative population database. This work represents an important methodological step toward complementing traditional AMR surveillance data practices. Data linkage to other data types, such as primary care, emergency, social, and biological data, may be the basis of achieving more precise data focused around AMR.
Assuntos
Infecção Hospitalar/epidemiologia , Armazenamento e Recuperação da Informação , Staphylococcus aureus Resistente à Meticilina/isolamento & purificação , Infecções Estafilocócicas/epidemiologia , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Alberta/epidemiologia , Feminino , Hospitalização/estatística & dados numéricos , Humanos , Masculino , Pessoa de Meia-Idade , Vigilância da População/métodos , Adulto JovemRESUMO
BACKGROUND: Identifying cases of disease in primary care electronic medical records (EMRs) is important for surveillance, research, quality improvement and clinical care. We aimed to develop and validate a case definition for type 1 diabetes mellitus using EMRs. METHODS: For this exploratory study, we used EMR data from the Southern Alberta Primary Care Network within the Canadian Primary Care Sentinel Surveillance Network (CPCSSN), for the period 2008 to 2016. For patients identified as having diabetes mellitus according to the existing CPCSSN case definition, we asked family physicians to confirm the diabetes subtype, to create the reference standard. We used 3 decision-tree classification algorithms and least absolute shrinkage and selection operator logistic regression to identify variables that correctly distinguished between type 1 and type 2 diabetes cases. RESULTS: We identified a total of 1309 people with type 1 or type 2 diabetes, 110 of whom were confirmed by their physicians as having type 1 diabetes. Two machine learning algorithms were useful in identifying these cases in the EMRs. The first algorithm used "type 1" text words or age less than 22 years at time of initial diabetes diagnosis; this algorithm had sensitivity 42.7% (95% confidence interval [CI] 33.5%-52.5%), specificity 99.3% (95% CI 98.6%-99.7%), positive predictive value 85.5% (95% CI 72.8%-93.1%) and negative predictive value 94.9% (95% CI 93.5%-96.1%). The second algorithm used a combination of free-text terms, insulin prescriptions and age; it had sensitivity 87.3% (95% CI 79.2%-92.6%), specificity 85.4% (95% CI 83.2%-87.3%), positive predictive value 35.6% (95% CI 29.9%-41.6%) and negative predictive value 98.6% (95% CI 97.7%-99.2%). INTERPRETATION: We used machine learning to develop and validate 2 case definitions that achieve different goals in distinguishing between type 1 and type 2 diabetes in CPCSSN data. Further validation and testing with a larger and more diverse sample are recommended.
RESUMO
Importance: The 2017 American College of Cardiology and American Heart Association (ACC/AHA) blood pressure (BP) guidelines redefined hypertension using a BP threshold of 130/80 mm Hg or greater and applied a treatment target of less than 130/80 mm Hg. Objective: To evaluate the potential change in the diagnosis, treatment, and control of hypertension in a Canadian cohort of patients with hypertension attending primary care practices using the ACC/AHA guidelines. Design, Setting, and Participants: This cross-sectional study used primary care practices across Canada electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network, extracted as of June 30, 2015. Adults with at least 1 primary care encounter in the previous 2 years (July 1, 2013, to June 30, 2015) were included in the study. Those with current hypertension were identified using a validated definition consisting of diagnoses, billing codes, and/or antihypertensive medication from within the primary care electronic medical record. Data analysis was conducted from December 2017 to July 2018. Main Outcomes and Measures: Proportion of individuals with a diagnosis of hypertension, prescribed antihypertensive medication, and meeting treatment BP targets. Results: Of the 594â¯492 Canadian participants included in the study, 144â¯348 (24.2%) had hypertension (45.6% male; mean [SD] age, 65.5 [14.5] years). On applying the ACC/AHA guidelines, 252â¯279 individuals (42.4%) were considered hypertensive and half (51.0%; 95% CI, 50.8%-51.2%) were prescribed an antihypertensive medication. Individuals who were not previously considered to have hypertension but were reclassified as having elevated BP using the lower cutoff of 130/80 mm Hg or greater tended to be younger and were at lower cardiovascular risk. There was a shift toward more individuals requiring antihypertensive treatment, particularly in the lower-risk categories. The crude prevalence of hypertension increased from 13.3% to 32.0% in those aged 18 to 64 years, and of those aged 65 years and older, 16.6% more individuals were reclassified as having hypertension (from 55.2% to 71.8%). Only 12.3% of those who were considered at high risk were reclassified as hypertensive. Conclusions and Relevance: Adoption of the ACC/AHA BP guidelines would result in a near doubling in the prevalence of hypertension in Canada. The changes would largely affect individuals who are younger and at low to moderate cardiovascular risk.
Assuntos
Anti-Hipertensivos/uso terapêutico , Determinação da Pressão Arterial , Hipertensão , Atenção Primária à Saúde , Idoso , Determinação da Pressão Arterial/métodos , Determinação da Pressão Arterial/normas , Determinação da Pressão Arterial/estatística & dados numéricos , Canadá/epidemiologia , Estudos de Coortes , Estudos Transversais , Feminino , Pesquisas sobre Atenção à Saúde , Humanos , Hipertensão/diagnóstico , Hipertensão/tratamento farmacológico , Hipertensão/epidemiologia , Masculino , Pessoa de Meia-Idade , Guias de Prática Clínica como Assunto , Prevalência , Atenção Primária à Saúde/métodos , Atenção Primária à Saúde/normas , Atenção Primária à Saúde/estatística & dados numéricos , Fatores de RiscoRESUMO
Objectives: Data derived from primary care electronic medical records (EMRs) are being used for research and surveillance. Case definitions are required to identify patients with specific conditions in EMR data with a degree of accuracy. The purpose of this study is to identify and provide a summary of case definitions that have been validated in primary care EMR data. Materials and Methods: We searched MEDLINE and Embase (from inception to June 2016) to identify studies that describe case definitions for clinical conditions in EMR data and report on the performance metrics of these definitions. Results: We identified 40 studies reporting on case definitions for 47 unique clinical conditions. The studies used combinations of International Classification of Disease version 9 (ICD-9) codes, Read codes, laboratory values, and medications in their algorithms. The most common validation metric reported was positive predictive value, with inconsistent reporting of sensitivity and specificity. Discussion: This review describes validated case definitions derived in primary care EMR data, which can be used to understand disease patterns and prevalence among primary care populations. Limitations include incomplete reporting of performance metrics and uncertainty regarding performance of case definitions across different EMR databases and countries. Conclusion: Our review found a significant number of validated case definitions with good performance for use in primary care EMR data. These could be applied to other EMR databases in similar contexts and may enable better disease surveillance when using clinical EMR data. Consistent reporting across validation studies using EMR data would facilitate comparison across studies. Systematic review registration: PROSPERO CRD42016040020 (submitted June 8, 2016, and last revised June 14, 2016).