Artificial intelligence-assisted clinical decision support for childhood asthma management: A randomized clinical trial.

RATIONALE: Clinical decision support (CDS) tools leveraging electronic health records (EHRs) have been an approach for addressing challenges in asthma care but remain under-studied through clinical trials. OBJECTIVES: To assess the effectiveness and efficiency of Asthma-Guidance and Prediction System (A-GPS), an Artificial Intelligence (AI)-assisted CDS tool, in optimizing asthma management through a randomized clinical trial (RCT). METHODS: This was a single-center pragmatic RCT with a stratified randomization design conducted for one year in the primary care pediatric practice of the Mayo Clinic, MN. Children (<18 years) diagnosed with asthma receiving care at the study site were enrolled along with their 42 primary care providers. Study subjects were stratified into three strata (based on asthma severity, asthma care status, and asthma diagnosis) and were blinded to the assigned groups. MEASUREMENTS: Intervention was a quarterly A-GPS report to clinicians including relevant clinical information for asthma management from EHRs and machine learning-based prediction for risk of asthma exacerbation (AE). Primary endpoint was the occurrence of AE within 1 year and secondary outcomes included time required for clinicians to review EHRs for asthma management. MAIN RESULTS: Out of 555 participants invited to the study, 184 consented for the study and were randomized (90 in intervention and 94 in control group). Median age of 184 participants was 8.5 years. While the proportion of children with AE in both groups decreased from the baseline (P = 0.042), there was no difference in AE frequency between the two groups (12% for the intervention group vs. 15% for the control group, Odds Ratio: 0.82; 95%CI 0.374-1.96; P = 0.626) during the study period. For the secondary end points, A-GPS intervention, however, significantly reduced time for reviewing EHRs for asthma management of each participant (median: 3.5 min, IQR: 2-5), compared to usual care without A-GPS (median: 11.3 min, IQR: 6.3-15); p<0.001). Mean health care costs with 95%CI of children during the trial (compared to before the trial) in the intervention group were lower than those in the control group (-$1,036 [-$2177, $44] for the intervention group vs. +$80 [-$841, $1000] for the control group), though there was no significant difference (p = 0.12). Among those who experienced the first AE during the study period (n = 25), those in the intervention group had timelier follow up by the clinical care team compared to those in the control group but no significant difference was found (HR = 1.93; 95% CI: 0.82-1.45, P = 0.10). There was no difference in the proportion of duration when patients had well-controlled asthma during the study period between the intervention and the control groups. CONCLUSIONS: While A-GPS-based intervention showed similar reduction in AE events to usual care, it might reduce clinicians' burden for EHRs review resulting in efficient asthma management. A larger RCT is needed for further studying the findings. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT02865967.

Asthma-associated comorbidities in children with and without secondhand smoke exposure.

BACKGROUND: Secondhand smoke (SHS) exposure is known to trigger asthma, but asthma disease severity and comorbidities in children exposed to SHS are not very well quantified. OBJECTIVE: To identify comorbidities and understand health care usage in children with asthma exposed to SHS (cases) compared with children with asthma but without SHS exposure (controls). METHODS: A retrospective nested matched case-and-control study was conducted with children 5 to 18 years old who were enrolled in the Pediatric Asthma Management Program. Pulmonary function testing (spirometry, methacholine challenges, and exhaled nitric oxide) and body mass index were reviewed. Influenza vaccination rates, oral steroid usage, emergency department visits, and hospitalizations were assessed. Network analysis of the 2 groups also was conducted to evaluate for any associations between the variables. RESULTS: Cases had significantly higher body mass index percentiles (>75%, odds ratio [OR] 1.64, 95% confidence interval [CI] 1.22-2.2, P = .001). Cases were less likely to have had a methacholine challenge (OR 0.49, 95% CI 0.36-0.68, P < .001) and an exhaled nitric oxide (OR 0.6, 95% CI 0.37-0.97, P = .04) performed than controls. The ratio of forced expiration volume in 1 second to forced vital capacity and forced expiration volume in 1 second were lower in cases than in controls (P < .05). Cases were less likely to have received an influenza vaccination (OR 0.61, 95% CI 0.45-0.82, P = .001) than controls. Unsupervised multivariable network analysis suggested a lack of discrete and unique subgroups between cases and controls. CONCLUSION: Children with asthma exposed to SHS are more likely to have comorbid conditions such as obesity, more severe asthma, and less health care usage than those not exposed to SHS. Smoking cessation interventions and addressing health disparities could be crucial in this vulnerable population.

Outcomes of stepping down asthma medications in a guideline-based pediatric asthma management program.

BACKGROUND: Little is known about outcomes after stepping down asthma medications within an asthma management program. OBJECTIVE: To determine outcomes of stepping down asthma medications in a pediatric asthma management program. METHODS: We performed a retrospective study of 5- to 18-year-old children with asthma in an integrated primary care practice in the United States. Data were included on participants from March 1, 2009, until December 31, 2011. We first determined whether a child was eligible for step down and next recorded whether a step-down attempt was made and if the attempt was successful. In addition to descriptive statistics for the sample demographics and the outcomes of stepping down, univariate and multivariate analyses were performed to determine predictors of successful asthma medication step-down attempts. RESULTS: Of the 477 children sampled for this study, 264 (55.3%) had a guideline-eligible opportunity to step down asthma medications. An attempted step down occurred in only 89 (33.7%) of children who had guideline-eligible opportunities. A total of 166 children (34.8%) attempted a step down of asthma medication at least once (including those guideline ineligible to step down). Of children with follow-up, 96 (71.6%) of step-down attempts were successful. Time of year (any season except fall) when the step down was attempted predicted successful step down in univariate and multivariate analysis (odds ratio = 3.81; 95% confidence interval, 1.23-11.85; P = .02). Being guideline eligible for step down predicted successful step down in univariate analysis only (odds ratio = 2.51; 95% confidence interval, 1.16-5.43; P = .02). CONCLUSION: Our findings from this sample of children participating in an asthma management program suggest that stepping down asthma medication based on National Asthma Education and Prevention Program 3 guidelines is frequently successful.

A program of anticipatory guidance for the prevention of emergency department visits for ear pain.

OBJECTIVE: To test whether well-child care visit anticipatory guidance can safely reduce emergency department (ED) visits. DESIGN: Retrospective analysis comparing an intervention site with control sites using a "difference-in-differences" regression model. SETTING: Primary care practices at the Mayo Clinic. PARTICIPANTS: Children who attended a 15-month well-child care visit. INTERVENTIONS: Nurses provided standardized education and prescribed antipyrine-benzocaine otic drops at the 15-month well-child care visit. Education focused on controlling otalgia, recognizing signs of more serious illness, and decreasing the sense of medical urgency for uncomplicated ear pain. MAIN OUTCOME MEASURES: Visit rates for ear pain during the ensuing year were compared in 4 retrospective cohorts: the intervention cohort (n = 191), a cohort from the same practice the preceding year (n = 168), and as controls, cohorts from these same years at other primary care sites not adopting this intervention (n = 133 and 126). RESULTS: After the intervention, ED visits for ear pain decreased 80%; urgent care visits, 40%; and primary care visits, 28%, with no significant change in the control sites' visit use during this time. Regression models incorporating patient characteristics and comparing the changes between sites across time supported the belief that the decline in ED use was significant (P = .009), with no significant change in urgent care (P = .33) or primary care (P = .14) use. On questionnaires, more than 80% of parents whose children had experienced subsequent ear pain responded that the program helped them avoid an ED or after-hours visit and strongly recommended continuing the education program. CONCLUSION: Nurse-administered anticipatory guidance reduced ED visits for ear pain in toddlers and was well appreciated by parents.