Achieving high inter-rater reliability in establishing data labels: a retrospective chart review study.

BACKGROUND: In medical research, the effectiveness of machine learning algorithms depends heavily on the accuracy of labeled data. This study aimed to assess inter-rater reliability (IRR) in a retrospective electronic medical chart review to create high quality labeled data on comorbidities and adverse events (AEs). METHODS: Six registered nurses with diverse clinical backgrounds reviewed patient charts, extracted data on 20 predefined comorbidities and 18 AEs. All reviewers underwent four iterative rounds of training aimed to enhance accuracy and foster consensus. Periodic monitoring was conducted at the beginning, middle, and end of the testing phase to ensure data quality. Weighted Kappa coefficients were calculated with their associated 95% confidence intervals (CIs). RESULTS: Seventy patient charts were reviewed. The overall agreement, measured by Conger's Kappa, was 0.80 (95% CI: 0.78-0.82). IRR scores remained consistently high (ranging from 0.70 to 0.87) throughout each phase. CONCLUSION: Our study suggests the detailed manual for chart review and structured training regimen resulted in a consistently high level of agreement among our reviewers during the chart review process. This establishes a robust foundation for generating high-quality labeled data, thereby enhancing the potential for developing accurate machine learning algorithms.

Real-world Use and Outcomes of Sodium-glucose Cotransporter-2 Inhibitors in Adults With Diabetes and Heart Failure: A Population-level Cohort Study in Alberta, Canada.

OBJECTIVES: Since 2016, clinical guidelines have recommended sodium-glucose cotransporter-2 inhibitors (SGLT2is) for people with type 2 diabetes with heart failure. We examined SGLT2i dispensation, factors associated with dispensation, and heart failure hospitalization and all-cause mortality in people with diabetes and heart failure. METHODS: This retrospective, population-based cohort study, identified people with diabetes and heart failure between Jan 1, 2014 to Dec 31, 2017 in Alberta, Canada and followed them for a minimum of three years for SGLT2i dispensation and outcomes. Multivariate logistic regression assessed the factors associated with SGTL2i dispensation. Propensity scores were used with regression adjustment to estimate the effect of SGLT2i treatment on heart failure hospitalization. RESULTS: Among 22,025 individuals with diabetes and heart failure (43.4% women, mean age 74.7±11.8 years), only 10.2% were dispensed an SGLT2i. Male sex, age <65 years, a higher baseline A1C, no chronic kidney disease, presence of atherosclerotic cardiovascular disease, and urban residence were associated with SGLT2i dispensation. Lower heart failure hospitalization rates were observed in those with SGLT2i dispensation (548.1 per 100 person years) vs those without (813.5 per 1,000 person years; p<0.001) and lower all-cause mortality in those with an SGLT2i than those without (48.5 per 1,000 person years vs 206.1 per 1,000 person years; p<0.001). Regression adjustment found SGLT2i therapy was associated with a 23% reduction in hospitalization. CONCLUSIONS: SGLT2is were dispensed to only 10% of people with diabetes and established heart failure, underscoring a significant care gap. SGLT2i use was associated with a real-world reduction in heart failure hospitalization and all-cause death. This study highlights an important opportunity to optimize SGLT2i use.

Evaluating the coding accuracy of type 2 diabetes mellitus among patients with non-alcoholic fatty liver disease.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) describes a spectrum of chronic fattening of liver that can lead to fibrosis and cirrhosis. Diabetes has been identified as a major comorbidity that contributes to NAFLD progression. Health systems around the world make use of administrative data to conduct population-based prevalence studies. To that end, we sought to assess the accuracy of diabetes International Classification of Diseases (ICD) coding in administrative databases among a cohort of confirmed NAFLD patients in Calgary, Alberta, Canada. METHODS: The Calgary NAFLD Pathway Database was linked to the following databases: Physician Claims, Discharge Abstract Database, National Ambulatory Care Reporting System, Pharmaceutical Information Network database, Laboratory, and Electronic Medical Records. Hemoglobin A1c and diabetes medication details were used to classify diabetes groups into absent, prediabetes, meeting glycemic targets, and not meeting glycemic targets. The performance of ICD codes among these groups was compared to this standard. Within each group, the total numbers of true positives, false positives, false negatives, and true negatives were calculated. Descriptive statistics and bivariate analysis were conducted on identified covariates, including demographics and types of interacted physicians. RESULTS: A total of 12,012 NAFLD patients were registered through the Calgary NAFLD Pathway Database and 100% were successfully linked to the administrative databases. Overall, diabetes coding showed a sensitivity of 0.81 and a positive predictive value of 0.87. False negative rates in the absent and not meeting glycemic control groups were 4.5% and 6.4%, respectively, whereas the meeting glycemic control group had a 42.2% coding error. Visits to primary and outpatient services were associated with most encounters. CONCLUSION: Diabetes ICD coding in administrative databases can accurately detect true diabetic cases. However, patients with diabetes who meets glycemic control targets are less likely to be coded in administrative databases. A detailed understanding of the clinical context will require additional data linkage from primary care settings.

Automated extraction of weight, height, and obesity in electronic medical records are highly valid.

Objective: Coding of obesity using the International Classification of Diseases (ICD) in healthcare administrative databases is under-reported and thus unreliable for measuring prevalence or incidence. This study aimed to develop and test a rule-based algorithm for automating the detection and severity of obesity using height and weight collected in several sections of the Electronic Medical Records (EMRs). Methods: In this cross-sectional study, 1904 inpatient charts randomly selected in three hospitals in Calgary, Canada between January and June 2015 were reviewed and linked with AllScripts Sunrise Clinical Manager EMRs. A rule-based algorithm was created which looks for patients' height and weight values recorded in EMRs. Clinical notes were split into sentences and searched for height and weight, and BMI was computed. Results: The study cohort consisted of 1904 patients with 50.8% females and 43.3% > 64 years of age. The final model to identify obesity within EMRs resulted in a sensitivity of 92.9%, specificity of 98.4%, positive predictive value of 96.7%, negative predictive value of 96.6%, and F1 score of 94.8%. Conclusions: This study developed a highly valid rule-based EMR algorithm that detects height and weight. This could allow large-scale analyses using obesity that were previously not possible.

BERT-Based Neural Network for Inpatient Fall Detection From Electronic Medical Records: Retrospective Cohort Study.

BACKGROUND: Inpatient falls are a substantial concern for health care providers and are associated with negative outcomes for patients. Automated detection of falls using machine learning (ML) algorithms may aid in improving patient safety and reducing the occurrence of falls. OBJECTIVE: This study aims to develop and evaluate an ML algorithm for inpatient fall detection using multidisciplinary progress record notes and a pretrained Bidirectional Encoder Representation from Transformers (BERT) language model. METHODS: A cohort of 4323 adult patients admitted to 3 acute care hospitals in Calgary, Alberta, Canada from 2016 to 2021 were randomly sampled. Trained reviewers determined falls from patient charts, which were linked to electronic medical records and administrative data. The BERT-based language model was pretrained on clinical notes, and a fall detection algorithm was developed based on a neural network binary classification architecture. RESULTS: To address various use scenarios, we developed 3 different Alberta hospital notes-specific BERT models: a high sensitivity model (sensitivity 97.7, IQR 87.7-99.9), a high positive predictive value model (positive predictive value 85.7, IQR 57.2-98.2), and the high F1-score model (F1=64.4). Our proposed method outperformed 3 classical ML algorithms and an International Classification of Diseases code-based algorithm for fall detection, showing its potential for improved performance in diverse clinical settings. CONCLUSIONS: The developed algorithm provides an automated and accurate method for inpatient fall detection using multidisciplinary progress record notes and a pretrained BERT language model. This method could be implemented in clinical practice to improve patient safety and reduce the occurrence of falls in hospitals.

Exploring the reliability of inpatient EMR algorithms for diabetes identification.

INTRODUCTION: Accurate identification of medical conditions within a real-time inpatient setting is crucial for health systems. Current inpatient comorbidity algorithms rely on integrating various sources of administrative data, but at times, there is a considerable lag in obtaining and linking these data. Our study objective was to develop electronic medical records (EMR) data-based inpatient diabetes phenotyping algorithms. MATERIALS AND METHODS: A chart review on 3040 individuals was completed, and 583 had diabetes. We linked EMR data on these individuals to the International Classification of Disease (ICD) administrative databases. The following EMR-data-based diabetes algorithms were developed: (1) laboratory data, (2) medication data, (3) laboratory and medications data, (4) diabetes concept keywords and (5) diabetes free-text algorithm. Combined algorithms used or statements between the above algorithms. Algorithm performances were measured using chart review as a gold standard. We determined the best-performing algorithm as the one that showed the high performance of sensitivity (SN), and positive predictive value (PPV). RESULTS: The algorithms tested generally performed well: ICD-coded data, SN 0.84, specificity (SP) 0.98, PPV 0.93 and negative predictive value (NPV) 0.96; medication and laboratory algorithm, SN 0.90, SP 0.95, PPV 0.80 and NPV 0.97; all document types algorithm, SN 0.95, SP 0.98, PPV 0.94 and NPV 0.99. DISCUSSION: Free-text data-based diabetes algorithm can yield comparable or superior performance to a commonly used ICD-coded algorithm and could supplement existing methods. These types of inpatient EMR-based algorithms for case identification may become a key method for timely resource planning and care delivery.

Use of Epic Electronic Health Record System for Health Care Research: Scoping Review.

BACKGROUND: Electronic health records (EHRs) enable health data exchange across interconnected systems from varied settings. Epic is among the 5 leading EHR providers and is the most adopted EHR system across the globe. Despite its global reach, there is a gap in the literature detailing how EHR systems such as Epic have been used for health care research. OBJECTIVE: The objective of this scoping review is to synthesize the available literature on use cases of the Epic EHR for research in various areas of clinical and health sciences. METHODS: We used established scoping review methods and searched 9 major information repositories, including databases and gray literature sources. To categorize the research data, we developed detailed criteria for 5 major research domains to present the results. RESULTS: We present a comprehensive picture of the method types in 5 research domains. A total of 4669 articles were screened by 2 independent reviewers at each stage, while 206 articles were abstracted. Most studies were from the United States, with a sharp increase in volume from the year 2015 onwards. Most articles focused on clinical care, health services research and clinical decision support. Among research designs, most studies used longitudinal designs, followed by interventional studies implemented at single sites in adult populations. Important facilitators and barriers to the use of Epic and EHRs in general were identified. Important lessons to the use of Epic and other EHRs for research purposes were also synthesized. CONCLUSIONS: The Epic EHR provides a wide variety of functions that are helpful toward research in several domains, including clinical and population health, quality improvement, and the development of clinical decision support tools. As Epic is reported to be the most globally adopted EHR, researchers can take advantage of its various system features, including pooled data, integration of modules and developing decision support tools. Such research opportunities afforded by the system can contribute to improving quality of care, building health system efficiencies, and conducting population-level studies. Although this review is limited to the Epic EHR system, the larger lessons are generalizable to other EHRs.

Implementing paediatric patient-reported outcome measures in outpatient asthma clinics: a feasibility assessment study.

OBJECTIVE: Implementation of patient-reported outcome measures (PROMs) is limited in paediatric routine clinical care. The KidsPRO programme has been codesigned to facilitate the implementation of PROMs in paediatric healthcare settings. Therefore, this study (1) describes the development of innovative KidsPRO programme and (2) reports on the feasibility of implementing PedsQL (Pediatric Quality of Life Inventory) PROM in asthma clinics using the KidsPRO programme. DESIGN: Feasibility assessment study. SETTING: Outpatient paediatric asthma clinics in the city of Calgary, Canada. PARTICIPANTS: Five paediatric patients, four family caregivers and three healthcare providers were recruited to pilot the implementation of PedsQL PROM using KidsPRO. Then, a survey was used to assess its feasibility among these study participants. MAIN OUTCOME MEASURES: Participants' understanding of using PROMs, the adequacy of support provided to them, the utility of using PROMs as part of their appointment, and their satisfaction with using PROMs. ANALYSES: The quantitative data generated through closed-ended questions was analysed and represented in the form of bar charts for each category of study participants (ie, patients, their family caregivers and healthcare providers). The qualitative data generated through the open-ended questions were content analysed and categorised into themes. RESULTS: The experience of using PROMs was overwhelmingly positive among patients and their family caregivers, results were mixed among healthcare providers. Qualitative data collected through open-ended questions also complemented the quantitative findings. CONCLUSION: The evidence from this study reveals that the implementation of PROMs in routine paediatric clinical care asthma clinics in Alberta is seems to be feasible.

Color coded health data: factors related to willingness to share health information in South Asian community members in Canada.

Introduction: Data unavailability poses multiple challenges in many health fields, especially within ethnic subgroups in Canada, who may be hesitant to share their health data with researchers. Since health information availability is controlled by the participant, it is important to understand the willingness to share health information by an ethnic population to increase data availability within ethnocultural communities. Methods: We employed a qualitative descriptive approach to better understand willingness to share health information by South Asian participants and operated through a lens that considered the cultural and sociodemographic aspect of ethnocultural communities. A total of 22 in-depth interviews were conducted between March and July 2020. Results: The results of this study show that health researchers should aim to develop a mutually beneficial information-sharing partnership with communities, with an emphasis on the ethnocultural and socio-ecological aspects of health within populations. Conclusion: The findings support the need for culturally sensitive and respectful engagement with the community, ethically sound research practices that make participants feel comfortable in sharing their information, and an easy sharing process to share health information feasibly.

Cerebrovascular disease case identification in inpatient electronic medical record data using natural language processing.

BACKGROUND: Abstracting cerebrovascular disease (CeVD) from inpatient electronic medical records (EMRs) through natural language processing (NLP) is pivotal for automated disease surveillance and improving patient outcomes. Existing methods rely on coders' abstraction, which has time delays and under-coding issues. This study sought to develop an NLP-based method to detect CeVD using EMR clinical notes. METHODS: CeVD status was confirmed through a chart review on randomly selected hospitalized patients who were 18 years or older and discharged from 3 hospitals in Calgary, Alberta, Canada, between January 1 and June 30, 2015. These patients' chart data were linked to administrative discharge abstract database (DAD) and Sunrise™ Clinical Manager (SCM) EMR database records by Personal Health Number (a unique lifetime identifier) and admission date. We trained multiple natural language processing (NLP) predictive models by combining two clinical concept extraction methods and two supervised machine learning (ML) methods: random forest and XGBoost. Using chart review as the reference standard, we compared the model performances with those of the commonly applied International Classification of Diseases (ICD-10-CA) codes, on the metrics of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULT: Of the study sample (n = 3036), the prevalence of CeVD was 11.8% (n = 360); the median patient age was 63; and females accounted for 50.3% (n = 1528) based on chart data. Among 49 extracted clinical documents from the EMR, four document types were identified as the most influential text sources for identifying CeVD disease ("nursing transfer report," "discharge summary," "nursing notes," and "inpatient consultation."). The best performing NLP model was XGBoost, combining the Unified Medical Language System concepts extracted by cTAKES (e.g., top-ranked concepts, "Cerebrovascular accident" and "Transient ischemic attack"), and the term frequency-inverse document frequency vectorizer. Compared with ICD codes, the model achieved higher validity overall, such as sensitivity (25.0% vs 70.0%), specificity (99.3% vs 99.1%), PPV (82.6 vs. 87.8%), and NPV (90.8% vs 97.1%). CONCLUSION: The NLP algorithm developed in this study performed better than the ICD code algorithm in detecting CeVD. The NLP models could result in an automated EMR tool for identifying CeVD cases and be applied for future studies such as surveillance, and longitudinal studies.

Development of machine learning models for the detection of surgical site infections following total hip and knee arthroplasty: a multicenter cohort study.

BACKGROUND: Population based surveillance of surgical site infections (SSIs) requires precise case-finding strategies. We sought to develop and validate machine learning models to automate the process of complex (deep incisional/organ space) SSIs case detection. METHODS: This retrospective cohort study included adult patients (age ≥ 18 years) admitted to Calgary, Canada acute care hospitals who underwent primary total elective hip (THA) or knee (TKA) arthroplasty between Jan 1st, 2013 and Aug 31st, 2020. True SSI conditions were judged by the Alberta Health Services Infection Prevention and Control (IPC) program staff. Using the IPC cases as labels, we developed and validated nine XGBoost models to identify deep incisional SSIs, organ space SSIs and complex SSIs using administrative data, electronic medical records (EMR) free text data, and both. The performance of machine learning models was assessed by sensitivity, specificity, positive predictive value, negative predictive value, F1 score, the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision-recall curve (PR AUC). In addition, a bootstrap 95% confidence interval (95% CI) was calculated. RESULTS: There were 22,059 unique patients with 27,360 hospital admissions resulting in 88,351 days of hospital stay. This included 16,561 (60.5%) TKA and 10,799 (39.5%) THA procedures. There were 235 ascertained SSIs. Of them, 77 (32.8%) were superficial incisional SSIs, 57 (24.3%) were deep incisional SSIs, and 101 (42.9%) were organ space SSIs. The incidence rates were 0.37 for superficial incisional SSIs, 0.21 for deep incisional SSIs, 0.37 for organ space and 0.58 for complex SSIs per 100 surgical procedures, respectively. The optimal XGBoost models using administrative data and text data combined achieved a ROC AUC of 0.906 (95% CI 0.835-0.978), PR AUC of 0.637 (95% CI 0.528-0.746), and F1 score of 0.79 (0.67-0.90). CONCLUSIONS: Our findings suggest machine learning models derived from administrative data and EMR text data achieved high performance and can be used to automate the detection of complex SSIs.

The incidence rates of surgical site infections following total hip and knee arthroplasty were 0.5 and 0.52 per 100 surgical procedures. The incidence of SSIs varied significantly between care facilities (ranging from 0.53 to 1.71 per 100 procedures). The optimal machine learning model achieved a ROC AUC of 0.906 (95% CI 0.835­0.978), PR AUC of 0.637 (95% CI 0.528­0.746), and F1 score of 0.79 (0.67­0.90).

Association of co-morbidity with acute stroke mortality by age and time since stroke: A population-based study.

OBJECTIVE: To examine whether the association of co-morbidity with mortality after acute stroke is influenced by stroke type, age, sex, or time since stroke. MATERIALS AND METHODS: We conducted a province-wide population-based study using linked administrative databases to identify all admissions for acute stroke between 2007-2018 in Alberta, Canada. We used Cox proportional hazard models to determine the association of severe co-morbidity based on the Charlson Co-morbidity Index with 1-year mortality after stroke, assessing for effect modification by stroke type, age, and sex, and with adjustment for estimated stroke severity, comprehensive stroke centre care, hypertension, atrial fibrillation, and year of study. We used a piecewise model to analyze the impact of co-morbidity across four time periods. RESULTS: We had 28,672 patients in our final cohort (87.8% ischemic stroke). The hazard of mortality with severe co-morbidity was higher for individuals with ischemic stroke (adjusted hazard ratio [aHR] 2.20, 95% CI 2.07-2.32) compared to those with intracerebral hemorrhage (aHR 1.70, 95% CI 1.51-1.92; pint<0.001), and higher in individuals under age 75 (aHR 3.20, 95% CI 2.90-3.53) compared to age ≥75 (aHR 1.93, 95% CI 1.82-2.05, pint<0.001). There was no interaction by sex. The hazard ratio increased in a graded fashion at younger ages and was higher after the first 30 days of acute stroke. CONCLUSION: There was a stronger association between co-morbidity and mortality at younger age and in the subacute phase of stroke. Further research is needed to determine the reason for these findings and identify ways to improve outcomes among those with stroke and co-morbid conditions at young age.

Uptake of pediatric patient-reported outcome and experience measures and challenges associated with their implementation in Alberta: a mixed-methods study.

BACKGROUND: Implementing Patient-reported Outcome Measures (PROMs) and Patient-reported Experience Measures (PREMs) is an effective way to deliver patient- and family-centered care (PFCC). Although Alberta Health Services (AHS) is Canada's largest and fully integrated health system, PROMs and PREMs are yet to be routinely integrated into the pediatric healthcare system. This study addresses this gap by investigating the current uptake, barriers, and enablers for integrating PROMs and PREMs in Alberta's pediatric healthcare system. METHODS: Pediatric clinicians and academic researchers with experience using PROMs and PREMs were invited to complete a quantitative survey. Additionally, key stakeholders were qualitatively interviewed to understand current challenges in implementing pediatric PROMs and PREMs within AHS. Quantitative data gathered from 22 participants were descriptively analyzed, and qualitative data from 14 participants were thematically analyzed. RESULTS: Participants identified 33 PROMs and 6 PREMs showing diversity in the types of pediatric PROMs and PREMs currently being used in Alberta and their mode of administration. The qualitatively identified challenges were associated with patients, family caregivers, and clinicians. The absence of system-level support, such as integration within electronic medical records, is considered a significant system-level challenge. CONCLUSIONS: The significant variation in the types of PROMs and PREMs used, the rationale for their use, and their mode of administration demonstrate the diverse and sporadic use of these measures in Alberta. These findings highlight the need for province-wide uniform implementation of pediatric PROMs and PREMs in Alberta. Our results could benefit healthcare organizations in developing evidence-based PROM and PREM implementation strategies in pediatrics.

Urban design and cardio-metabolic risk factors.

Accumulating evidence suggests that the built environment may be associated with cardiovascular disease via its influence on health behaviours. The aim of this study was to estimate the associations between traditional and novel neighbourhood built environment metrics and clinically assessed cardio-metabolic risk factors among a sample of adults in Canada. A total of 7171 participants from Albertas Tomorrow Project living in Alberta, Canada, were included. Cardio-metabolic risk factors were clinically measured. Two composite built environment metrics of traditional walkability and space syntax walkability were calculated. Among men, space syntax walkability was negatively associated with systolic and diastolic blood pressure (b = -0.87, 95% CI -1.43, -0.31 and b = -0.45, 95% CI -0.86, -0.04, respectively). Space syntax walkability was also associated with lower odds of overweight/obese among women and men (OR = 0.93, 95% CI 0.87, 0.99 and OR = 0.88, 95% CI 0.79, 0.97, respectively). No significant associations were observed between traditional walkability and cardio-metabolic outcomes. This study showed that the novel built environment metric based on the space syntax theory was associated with some cardio-metabolic risk factors.

Design Principles in mHealth Interventions for Sustainable Health Behavior Changes: Protocol for a Systematic Review.

BACKGROUND: In recent years, mHealth has increasingly been used to deliver behavioral interventions for disease prevention and self-management. Computing power in mHealth tools can provide unique functions beyond conventional interventions in provisioning personalized behavior change recommendations and delivering them in real time, supported by dialogue systems. However, design principles to incorporate these features in mHealth interventions have not been systematically evaluated. OBJECTIVE: The goal of this review is to identify best practices for the design of mHealth interventions targeting diet, physical activity, and sedentary behavior. We aim to identify and summarize the design characteristics of current mHealth tools with a focus on the following features: (1) personalization, (2) real-time functions, and (3) deliverable resources. METHODS: We will conduct a systematic search of electronic databases, including MEDLINE, CINAHL, Embase, PsycINFO, and Web of Science for studies published since 2010. First, we will use keywords that combine mHealth, interventions, chronic disease prevention, and self-management. Second, we will use keywords that cover diet, physical activity, and sedentary behavior. Literature found in the first and second steps will be combined. Finally, we will use keywords for personalization and real-time functions to limit the results to interventions that have reported these design features. We expect to perform narrative syntheses for each of the 3 target design features. Study quality will be evaluated using the Risk of Bias 2 assessment tool. RESULTS: We have conducted a preliminary search of existing systematic reviews and review protocols on mHealth-supported behavior change interventions. We have identified several reviews that aimed to evaluate the efficacy of mHealth behavior change interventions in a range of populations, evaluate methodologies for assessing mHealth behavior change randomized trials, and assess the diversity of behavior change techniques and theories in mHealth interventions. However, syntheses on the unique features of mHealth intervention design are absent in the literature. CONCLUSIONS: Our findings will provide a basis for developing best practices for designing mHealth tools for sustainable behavior change. TRIAL REGISTRATION: PROSPERO CRD42021261078; https://tinyurl.com/m454r65t. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/39093.

Hypertension identification using inpatient clinical notes from electronic medical records: an explainable, data-driven algorithm study.

BACKGROUND: Case identification is important for health services research, measuring health system performance and risk adjustment, but existing methods based on manual chart review or diagnosis codes can be expensive, time consuming or of limited validity. We aimed to develop a hypertension case definition in electronic medical records (EMRs) for inpatient clinical notes using machine learning. METHODS: A cohort of patients 18 years of age or older who were discharged from 1 of 3 Calgary acute care facilities (1 academic hospital and 2 community hospitals) between Jan. 1 and June 30, 2015, were randomly selected, and we compared the performance of EMR phenotype algorithms developed using machine learning with an algorithm based on the Canadian version of the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD), in identifying patients with hypertension. Hypertension status was determined by chart review, the machine-learning algorithms used EMR notes and the ICD algorithm used the Discharge Abstract Database (Canadian Institute for Health Information). RESULTS: Of our study sample (n = 3040), 1475 (48.5%) patients had hypertension. The group with hypertension was older (median age of 71.0 yr v. 52.5 yr for those patients without hypertension) and had fewer females (710 [48.2%] v. 764 [52.3%]). Our final EMR-based models had higher sensitivity than the ICD algorithm (> 90% v. 47%), while maintaining high positive predictive values (> 90% v. 97%). INTERPRETATION: We found that hypertension tends to have clear documentation in EMRs and is well classified by concept search on free text. Machine learning can provide insights into how and where conditions are documented in EMRs and suggest nonmachine-learning phenotypes to implement.

Variation in Testing for and Incidence of Celiac Autoimmunity in Canada: A Population-Based Study.

BACKGROUND & AIMS: The incidence of biopsy-confirmed celiac disease has increased. However, few studies have explored the incidence of celiac autoimmunity based on positive serology results. METHODS: A population-based cohort study assessed testing of tissue transglutaminase antibodies (tTG-IgA) in Alberta from 2012 to 2020. After excluding prevalent cases, incident celiac autoimmunity was defined as the first positive tTG-IgA result between 2015 and 2020. Testing and incidence rates for celiac autoimmunity were calculated per 1000 and 100,000 person-years, respectively. Incidence rate ratios (IRRs) were calculated to identify differences by demographic and regional factors. Average annual percent changes (AAPCs) assessed trends over time. RESULTS: The testing rate of tTG-IgA was 20.2 per 1000 person-years and remained stable from 2012 to 2020 (AAPC, 1.2%; 95% confidence interval [CI], -0.5 to 2.9). Testing was higher in female patients (IRR, 1.66; 95% CI, 1.65-1.66), those living in metropolitan areas (IRR, 1.39; 95% CI, 1.38-1.40), and in areas of lower socioeconomic deprivation (lowest compared to highest IRR, 1.24; 95% CI, 1.23-1.25). Incidence of celiac autoimmunity was 33.8 per 100,000 person-years and increased from 2015 to 2020 (AAPC, 6.2%; 95% CI, 3.1-9.5). Among those with tTG-IgA results ≥10 times the upper limit of normal, the incidence was 12.9 per 100,000 person-years. The incidence of celiac autoimmunity was higher in metropolitan settings (IRR, 1.28; 95% CI, 1.21-1.35) and in the least socioeconomically deprived areas compared to the highest (IRR, 1.22; 95% CI, 1.14-1.32). CONCLUSIONS: Incidence of celiac autoimmunity is high and increasing, despite stable testing rates. Variation in testing patterns may lead to underreporting the incidence of celiac autoimmunity in nonmetropolitan areas and more socioeconomically deprived neighborhoods.

A comparison of machine learning algorithms and traditional regression-based statistical modeling for predicting hypertension incidence in a Canadian population.

Risk prediction models are frequently used to identify individuals at risk of developing hypertension. This study evaluates different machine learning algorithms and compares their predictive performance with the conventional Cox proportional hazards (PH) model to predict hypertension incidence using survival data. This study analyzed 18,322 participants on 24 candidate features from the large Alberta's Tomorrow Project (ATP) to develop different prediction models. To select the top features, we applied five feature selection methods, including two filter-based: a univariate Cox p-value and C-index; two embedded-based: random survival forest and least absolute shrinkage and selection operator (Lasso); and one constraint-based: the statistically equivalent signature (SES). Five machine learning algorithms were developed to predict hypertension incidence: penalized regression Ridge, Lasso, Elastic Net (EN), random survival forest (RSF), and gradient boosting (GB), along with the conventional Cox PH model. The predictive performance of the models was assessed using C-index. The performance of machine learning algorithms was observed, similar to the conventional Cox PH model. Average C-indexes were 0.78, 0.78, 0.78, 0.76, 0.76, and 0.77 for Ridge, Lasso, EN, RSF, GB and Cox PH, respectively. Important features associated with each model were also presented. Our study findings demonstrate little predictive performance difference between machine learning algorithms and the conventional Cox PH regression model in predicting hypertension incidence. In a moderate dataset with a reasonable number of features, conventional regression-based models perform similar to machine learning algorithms with good predictive accuracy.

Training and experience of coding with the World Health Organization's International Classification of Diseases, Eleventh Revision.

BACKGROUND: The new International Classification of Diseases, Eleventh Revision for Mortality and Morbidity Statistics (ICD-11) was developed and released by the World Health Organization (WHO) in June 2018. Because ICD-11 incorporates new codes and features, training materials for coding with ICD-11 are urgently needed prior to its implementation. OBJECTIVE: This study outlines the development of ICD-11 training materials, training processes and experiences of clinical coders while learning to code using ICD-11. METHOD: Six certified clinical coders were recruited to code inpatient charts using ICD-11. Training materials were developed with input from experts from the Canadian Institute for Health Information and the WHO, and the clinical coders were trained to use the new classification. Monthly team meetings were conducted to enable discussions on coding issues and to select the correct ICD-11 codes. The training experience was evaluated using qualitative interviews, a questionnaire and a coding quiz. RESULTS: total of 3011 charts were coded using ICD-11. In general, clinical coders provided positive feedback regarding the training program. The average score for the coding quiz (multiple choice, True/False) was 84%, suggesting that the training program was effective. Feedback from the coders enabled the ICD-11 code content, electronic tooling and terminologies to be updated. CONCLUSION: This study provides a detailed account of the processes involved with training clinical coders to use ICD-11. Important findings from the interviews were reported at the annual WHO conferences, and these findings helped improve the ICD-11 browser and reference guide.

Automating data collection methods in electronic health record systems: a Social Determinant of Health (SDOH) viewpoint.

Social Determinant of Health (SDOH) data are important targets for research and innovation in Health Information Systems (HIS). The ways we envision SDOH in "smart" information systems will play a considerable role in shaping future population health landscapes. Current methods for data collection can capture wide ranges of SDOH factors, in standardised and non-standardised formats, from both primary and secondary sources. Advances in automating data linkage and text classification show particular promise for enhancing SDOH in HIS. One challenge is that social communication processes embedded in data collection are directly related to the inequalities that HIS attempt to measure and redress. To advance equity, it is imperative thatcare-providers, researchers, technicians, and administrators attend to power dynamics in HIS standards and practices. We recommend: 1. Investing in interdisciplinary and intersectoral knowledge generation and translation. 2. Developing novel methods for data discovery, linkage and analysis through participatory research. 3. Channelling information into upstream evidence-informed policy.