A diagnostic codes-based algorithm improves accuracy for identification of childhood asthma in archival data sets

Automated Interpretation of Lung Sounds by Deep Learning in Children With Asthma: Scoping Review and Strengths, Weaknesses, Opportunities, and Threats Analysis

BACKGROUND

The interpretation of lung sounds plays a crucial role in the appropriate diagnosis and management of pediatric asthma. Applying artificial intelligence (AI) to this task has the potential to better standardize assessment and may even improve its predictive potential.

OBJECTIVE

This study aims to objectively review the literature on AI-assisted lung auscultation for pediatric asthma and provide a balanced assessment of its strengths, weaknesses, opportunities, and threats.

METHODS

A scoping review on AI-assisted lung sound analysis in children with asthma was conducted across 4 major scientific databases (PubMed, MEDLINE Ovid, Embase, and Web of Science), supplemented by a gray literature search on Google Scholar, to identify relevant studies published from January 1, 2000, until May 23, 2023. The search strategy incorporated a combination of keywords related to AI, pulmonary auscultation, children, and asthma. The quality of eligible studies was assessed using the ChAMAI (Checklist for the Assessment of Medical Artificial Intelligence).

RESULTS

The search identified 7 relevant studies out of 82 (9%) to be included through an academic literature search, while 11 of 250 (4.4%) studies from the gray literature search were considered but not included in the subsequent review and quality assessment. All had poor to medium ChAMAI scores, mostly due to the absence of external validation. Identified strengths were improved predictive accuracy of AI to allow for prompt and early diagnosis, personalized management strategies, and remote monitoring capabilities. Weaknesses were the heterogeneity between studies and the lack of standardization in data collection and interpretation. Opportunities were the potential of coordinated surveillance, growing data sets, and new ways of collaboratively learning from distributed data. Threats were both generic for the field of medical AI (loss of interpretability) but also specific to the use case, as clinicians might lose the skill of auscultation.

CONCLUSIONS

To achieve the opportunities of automated lung auscultation, there is a need to address weaknesses and threats with large-scale coordinated data collection in globally representative populations and leveraging new approaches to collaborative learning.

Association Between the COI and Excess Health Care Utilization and Costs for ACSC

BACKGROUND AND OBJECTIVES

The authors of previous work have associated the Childhood Opportunity Index (COI) with increased hospitalizations for ambulatory care sensitive conditions (ACSC). The burden of this inequity on the health care system is unknown. We sought to understand health care resource expenditure in terms of excess hospitalizations, hospital days, and cost.

METHODS

We performed a retrospective cross-sectional study of the Pediatric Health Information Systems database, including inpatient hospitalizations between January 1, 2016 and December 31, 2022 for children <18 years of age. We compared ACSC hospitalizations, mortality, and cost across COI strata.

RESULTS

We identified 2 870 121 hospitalizations among 1 969 934 children, of which 44.5% (1 277 568/2 870 121) were for ACSCs. A total of 49.1% (331 083/674 548) of hospitalizations in the very low stratum were potentially preventable, compared with 39.7% (222 037/559 003) in the very high stratum (P < .001). After adjustment, lower COI was associated with higher odds of potentially preventable hospitalization (odds ratio 1.18, 95% confidence interval [CI] 1.17-1.19). Compared with the very high COI stratum, there were a total of 137 550 (95% CI 134 582-140 517) excess hospitalizations across all other strata, resulting in an excess cost of $1.3 billion (95% CI $1.28-1.35 billion). Compared with the very high COI stratum, there were 813 (95% CI 758-871) excess deaths, with >95% from the very low and low COI strata.

CONCLUSIONS

Children with lower neighborhood opportunity have increased risk of ACSC hospitalizations. The COI may identify communities in which targeted intervention could reduce health care utilization and costs.

Influenza Vaccination Is Associated With Lower Incidental Asthma Risk in Patients With Atopic Dermatitis: A Nationwide Cohort Study

Background

Atopic march refers to the natural history of atopic dermatitis (AD) in infancy followed by subsequent allergic rhinitis and asthma in later life. Respiratory viruses interact with allergic sensitization to promote recurrent wheezing and the development of asthma. We aimed to evaluate whether influenza vaccination reduces asthma risk in people with AD.

Methods

This cohort study was conducted retrospectively from 2000 to 2013 by the National Health Insurance Research Database (NHIRD). Patients with newly diagnosed AD (International Classification of Diseases, Ninth Revision, Clinical Modification code 691) were enrolled as the AD cohort. We matched each vaccinated patient with one non-vaccinated patient according to age and sex. We observed each participant until their first asthma event, or the end of the study on December 31, 2013, whichever came first.

Results

Our analyses included 4,414 people with a mean age of 53 years. Of these, 43.8 were male. The incidence density of asthma was 12.6 per 1,000 person-years for vaccinated patients, and 15.1 per 1000 person-years for non-vaccinated patients. The adjusted hazard ratio (aHR) of asthma in the vaccinated cohort relative to the non-vaccinated cohort was 0.69 (95% CI = 0.55–0.87). Vaccinated patients had a lower cumulative incidence of asthma than unvaccinated patients. Vaccinated participants in all age and sex groups trended toward a lower risk of asthma. People will reduce more asthma risk when taking shots every year.

Conclusion

Influenza vaccination was associated with lower asthma risk in patients with AD.

Rat-Bite Fever in the United States: An Analysis Using Multiple National Data Sources, 2001-2015

BACKGROUND

Rat-bite fever is a rare disease associated with rat bites or direct/indirect rodent contact.

METHODS

We examined rat-bite fever and rat-bite injury diagnoses in the United States during 2001-2015. We analyzed national, state, and Indian Health Service healthcare encounter datasets for rat-bite fever and rat-bite injury diagnoses. We calculated average-annual encounter rates per 1 000 000 persons.

RESULTS

Nationally, the rat-bite fever Emergency Department visit rate was 0.33 (95% confidence interval [CI], 0.19-0.47) and the hospitalization rate was 0.20 (95% CI, 0.17-0.24). The rat-bite injury Emergency Department visit rate was 10.51 (95% CI, 10.13-10.88) and the hospitalization rate was 0.27 (95% CI, 0.23-0.30). The Indian Health Service Emergency Department/outpatient visit rate was 3.00 for rat-bite fever and 18.89 for rat-bite injury. The majority of rat-bite fever encounters were among individuals 0-19 years of age.

CONCLUSIONS

Our results support the literature that rat-bite fever is rare and affects children and young adults. Targeted education could benefit specific risk groups.