10 December 2017 in Family Practice
Antimicrobial stewardship (AS) programs promote the optimal use of antimicrobials and safe patient care. With most antimicrobials prescribed in the ambulatory setting, establishing benchmark data is imperative to gauge the impact of future AS initiatives. To determine the frequency of potentially inappropriate antimicrobial prescribing in primary care practices in Manitoba, Canada and to assess the association between potentially inappropriate antimicrobial prescribing and patient, prescriber and practice-related factors. A retrospective cohort study using the Manitoba Primary Care Research Network repository of de-identified Electronic Medical Records from consenting primary care practices. Descriptive statistics and logistic regressions detailed patients with bacterial or viral infections of interest and antimicrobial prescriptions. Eighteen percent (n = 35 574) of primary care visits for common infections were associated with a potentially inappropriate antimicrobial prescription. Among antimicrobials prescribed to patients diagnosed with bacterial infections, 37.8% (n = 2168) had a potentially inappropriate antimicrobial prescribed and 19.6% (n = 1126) had an antimicrobial prescribed for a duration outside of guideline-based ranges. Female patients, younger age and less office visits were associated with potentially inappropriate antimicrobial prescribing for bacterial infections. Among physician visits for viral infection, 15.9% (n = 29 833) were associated with an antimicrobial prescription. Older patients, those with more comorbidity, more office visits and those who were seen in larger or rural practices, were associated with potentially inappropriate antimicrobial prescribing for viral infections. High frequency of potentially inappropriate antimicrobial prescribing, especially in certain patient populations, suggests the need for coordinated community-based AS programs to optimize prescribing and improve patient care.
1 October 2021 in Health Informatics Journal
This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model’s ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations.
1 May 2020 in Multiple Sclerosis and Related Disorders
1 June 2022 in Neurology Clinical Practice
Background and Objectives The COVID-19 pandemic has dramatically increased telehealth use. We assessed access to and use of telehealth care, including videoconferencing and usability of videoconferencing, among persons with multiple sclerosis (MS). Methods In Fall 2020, we surveyed participants in the North American Research Committee on Multiple Sclerosis Registry. Participants reported availability and receipt of MS care or education through telehealth. Participants who completed ≥1 live videoconferencing visit completed the Telehealth Usability Questionnaire (TUQ). We tested factors associated with access to and receipt of telehealth care using logistic regression. We tested factors associated with TUQ scores using quantile regression. Results Of the 8,434 participants to whom the survey was distributed, 6,043 responded (71.6%); 5,403 were eligible for analysis. Of the respondents, 4,337 (80.6%) were women, and they had a mean (SD) age of 63.2 (10.0) years. Overall, 2,889 (53.5%) reported access to MS care via telehealth, and 2,110 (39.1%) reported receipt of MS care via telehealth including 1,523 (28%) via videoconference. Among participants who reported telehealth was available, older age was associated with decreased odds of having a telehealth video visit; higher income and being physically active were associated with increased odds. Older age and moderate to very severe visual symptoms were associated with lower perceived usability of telehealth. Discussion Older age, lower socioeconomic status, and disease-related impairments are associated with less access to and use of telehealth services in people with MS. Barriers to telehealth should be addressed to avoid aggravating health care disparities when using digital medicine.
1 January 2022 in BioSystems
6 February 2018 in Journal of the American Heart Association
Background: As questions have been raised about the appropriateness of direct oral anticoagulant ( DOAC ) dosing among outpatients with atrial fibrillation, we examined this issue in patients being managed by primary care providers. Methods and Results: This was a retrospective cohort new‐user study using electronic medical records from 744 Canadian primary care clinicians. Potentially inappropriate DOAC prescribing was defined as prescribing lower or higher doses than those recommended by guidelines for patients with nonvalvular atrial fibrillation. Of the 6658 patients with nonvalvular atrial fibrillation who were prescribed a DOAC (mean age: 74.8; 55% male), 626 (9.4%) had a CHADS 2 score of 0, and 168 (2.5%) had a CHADS ‐ VAS c score of 0. Of the DOAC prescriptions, 527 (7.7%) were deemed potentially inappropriate: 496 (7.2%) were potentially underdosed, and 31 (0.5%) were prescribed a dose that was higher than recommended. Patients were more likely to be prescribed lower‐than‐recommended doses if they were female (adjusted odds ratio [ aOR ]: 1.3 [95% confidence interval ( CI ), 1.0–1.5]), had multiple comorbidities ( aOR: 1.4 [95% CI, 1.1–1.8])—particularly heart failure ( aOR : 1.6 [95% CI, 1.2–2.0]) or dementia ( aOR : 1.4 [95% CI, 1.1–1.8])—or if they were also taking aspirin ( aOR : 1.7 [95% CI, 1.3–2.1]) or nonsteroidal anti‐inflammatory drugs ( aOR : 1.2 [95% CI, 1.02–1.5]). Potentially inappropriate DOAC dosing was more common in rural practices ( aOR : 2.1 [95% CI, 1.7–2.6]) or smaller practices ( aOR : 1.9 [95% CI, 1.6–2.4] for practices smaller than median). Conclusions: The vast majority of DOAC prescriptions in our cohort of primary care–managed patients appeared to be for appropriate doses, particularly since prescribing a reduced dose of DOAC may be appropriate in frail patients or those taking other medications that predispose to bleeding.