Accuracy of Algorithms to Identify People with Atopic Dermatitis in Ontario Routinely Collected Health Databases

Artificial Intelligence: A Snapshot of Its Application in Chronic Inflammatory and Autoimmune Skin Diseases

Immuno-correlated dermatological pathologies refer to skin disorders that are closely associated with immune system dysfunction or abnormal immune responses. Advancements in the field of artificial intelligence (AI) have shown promise in enhancing the diagnosis, management, and assessment of immuno-correlated dermatological pathologies. This intersection of dermatology and immunology plays a pivotal role in comprehending and addressing complex skin disorders with immune system involvement. The paper explores the knowledge known so far and the evolution and achievements of AI in diagnosis; discusses segmentation and the classification of medical images; and reviews existing challenges, in immunological-related skin diseases. From our review, the role of AI has emerged, especially in the analysis of images for both diagnostic and severity assessment purposes. Furthermore, the possibility of predicting patients' response to therapies is emerging, in order to create tailored therapies.

A comparison of family physician and dermatologist topical corticosteroid prescriptions: A population-based cross-sectional study

BACKGROUND

Topical corticosteroids (TCS) are commonly prescribed to treat inflammatory skin diseases, and appropriate prescription is necessary for treatment success.

OBJECTIVE

To quantify differences between TCS prescribed by dermatologists at consultation and family physicians for patients treated for any skin condition.

METHODS

Using administrative health data in Ontario, we included all Ontario Drug Benefit recipients who filled at least one TCS prescription from a dermatologist at consultation and a family physician in the year prior between January 2014 and December 2019. We estimated mean differences and 95% confidence intervals in amount (in grams) and potency between the index dermatologist prescription and the highest and most recent family physician prescription amounts and potencies in the preceding year using linear mixed-effect models.

RESULTS

A total of 69,335 persons were included. The mean dermatologist amount was 34% larger than the highest amount and 54% larger than the most recent amount prescribed by family physicians. There were small but statistically significant differences in potency using established 7-category and 4-category potency classification systems.

CONCLUSIONS

Compared to family physicians, dermatologists prescribed substantially larger amounts and similarly potent TCS at consultation. Further research is needed to determine the effect of these differences on clinical outcomes.

Predicting the target specialty of referral notes to estimate per-specialty wait times with machine learning

Background

Currently, in Canada, existing health administrative data and hospital-inputted portal systems are used to measure the wait times to receiving a procedure or therapy after a specialist visit. However, due to missing and inconsistent labelling, estimating the wait time prior to seeing a specialist physician requires costly manual coding to label primary care referral notes.

Methods

In this work, we represent the notes using word-count vectors and develop a logistic regression machine learning model to automatically label the target specialist physician from a primary care referral note. These labels are not available in the administrative system. We also study the effects of note length (measured in number of tokens) and dataset size (measured in number of notes per target specialty) on model performance to help other researchers determine if such an approach may be feasible for them. We then calculate the wait time by linking the specialist type from a primary care referral to a full consultation visit held in Ontario, Canada health administrative data.

Results

For many target specialties, we can reliably (F1Score ≥ 0.70) predict the target specialist type. Doing so enables the automated measurement of wait time from family physician referral to specialist physician visit. Of the six specialties with wait times estimated using both 2008 and 2015 data, two had a substantial increase (defined as a change such that the original value lay outside the 95% confidence interval) in both median and 75th percentile wait times, one had a substantial decrease in both median and 75th percentile wait times, and three has non-substantial increases.

Conclusions

Automating these wait time measurements, which had previously been too time consuming and costly to evaluate at a population level, can be useful for health policy researchers studying the effects of policy decisions on patient access to care.

Sociodemographic characteristics and emergency department visits and inpatient hospitalizations for atopic dermatitis in Ontario: a cross-sectional study

BACKGROUND

Some jurisdictions experience sociodemographic disparities in atopic dermatitis care, including emergency department visits, but data from Canada are limited. Our objectives were to estimate the prevalence of atopic dermatitis in Ontario and to identify sociodemographic factors associated with emergency department visits and hospitalizations for this condition.

METHODS

We conducted a cross-sectional analysis of patients in the Electronic Medical Record Primary Care database linked with administrative health data for Ontario, Canada. We estimated period prevalence and health service utilization for atopic dermatitis from 2005 to 2015. We used multivariable log-binomial regression to calculate adjusted risk ratios (RRs) and 95% confidence intervals (CIs) for associations between local dermatologist density and the proportion of emergency department visits and hospitalizations for atopic dermatitis.

RESULTS

Among 249 984 patients, we identified 7812 with atopic dermatitis (period prevalence 2005-2015: 3.1%). Almost all physician visits for atopic dermatitis were to primary care physicians (> 99%). For every additional dermatologist per 100 000 population, the proportions of emergency department visits and hospitalizations for atopic dermatitis increased by 29% (RR 1.29, 95% CI 1.05-1.57). This relationship occurred in and around Toronto but was not consistent across the province.

INTERPRETATION

In Ontario, higher dermatologist density was not associated with lower emergency department utilization and hospitalization for atopic dermatitis; the association varied in different locales with similar dermatologist densities. Strategies to improve access to care for atopic dermatitis should be tailored to local contexts.