Using Artificial Intelligence to Label Free-Text Operative and Ultrasound Reports for Grading Pediatric Appendicitis.

PURPOSE: Data science approaches personalizing pediatric appendicitis management are hampered by small datasets and unstructured electronic medical records (EMR). Artificial intelligence (AI) chatbots based on large language models can structure free-text EMR data. We compare data extraction quality between ChatGPT-4 and human data collectors. METHODS: To train AI models to grade pediatric appendicitis preoperatively, several data collectors extracted detailed preoperative and operative data from 2100 children operated for acute appendicitis. Collectors were trained for the task based on satisfactory Kappa scores. ChatGPT-4 was prompted to structure free text from 103 random anonymized ultrasound and operative records in the dataset using the set variables and coding options, and to estimate appendicitis severity grade from the operative report. A pediatric surgeon then adjudicated all data, identifying errors in each method. RESULTS: Within the 44 ultrasound (42.7%) and 32 operative reports (31.1%) discordant in at least one field, 98% of the errors were found in the manual data extraction. The appendicitis grade was erroneously assigned manually in 29 patients (28.2%), and by ChatGPT-4 in 3 (2.9%). Across datasets, the use of the AI chatbot was able to avoid misclassification in 59.2% of the records including both reports and extracted data approximately 40 times faster. CONCLUSION: AI chatbot significantly outperformed manual data extraction in accuracy for ultrasound and operative reports, and correctly assigned the appendicitis grade. While wider validation is required and data safety concerns must be addressed, these AI tools show significant promise in improving the accuracy and efficiency of research data collection. LEVELS OF EVIDENCE: Level III.

Effectiveness of the BreatheSuite Device in Assessing the Technique of Metered-Dose Inhalers: Validation Study.

BACKGROUND: The majority of medications used in treating asthma and chronic obstructive pulmonary disease (COPD) are taken through metered-dose inhalers (MDIs). Studies have reported that most patients demonstrate poor inhaler technique, which has resulted in poor disease control. Digital Health applications have the potential to improve the technique and adherence of inhaled medications. OBJECTIVE: This study aimed to validate the effectiveness of the BreatheSuite MDI device in assessing the technique of taking a dose via an MDI. METHODS: The study was a validation study. Thirty participants who self-reported a diagnosis of asthma or COPD were recruited from community pharmacies in Newfoundland and Labrador, Canada. Participants used a BreatheSuite MDI device attached to a placebo MDI and resembled taking 3 doses. Pharmacists used a scoring sheet to evaluate the technique of using the MDI. An independent researcher compared the results of the pharmacist's scoring sheet with the results of the BreatheSuite device. RESULTS: This study found that the BreatheSuite MDI can objectively detect several errors in the MDI technique. The data recorded by the BreatheSuite MDI device showed that all participants performed at least one error in using the MDI. The BreatheSuite device captured approximately 40% (143/360) more errors compared to observation alone. The distribution of participants who performed errors in MDI steps as recorded by BreatheSuite compared to errors reported by observation alone were as follows: shaking before actuation, 33.3% (30/90) versus 25.5% (23/90); upright orientation of the inhaler during actuation, 66.7% (60/90) versus 18.87% (17/90); coordination (actuating after the start of inhalation), 76.6% (69/90) versus 35.5% (32/90); and duration of inspiration, 96.7% (87/90) versus 34.4% (31/90). CONCLUSIONS: The BreatheSuite MDI can objectively detect several errors in the MDI technique, which were missed by observation alone. It has the potential to enhance treatment outcomes among patients with chronic lung diseases.

A Digital Diabetes Prevention Program (Transform) for Adults With Prediabetes: Secondary Analysis.

BACKGROUND: The prevalence of diabetes is increasing among adults globally. Research has demonstrated that a diabetes prevention program (DPP), which focuses on developing and maintaining health-promoting lifestyle modifications, can prevent or delay the onset of type 2 diabetes among at-risk individuals. The implementation of a digitally adapted DPP has the potential to prevent prediabetes on a national and global scale by using technology and behavior change science. OBJECTIVE: This study aimed to investigate the effects of a novel digital therapeutic DPP (Transform) on weight loss, body mass index (BMI), exercise frequency, and work absenteeism. METHODS: This study was a secondary analysis of retrospective data of adults with prediabetes who were enrolled in the Transform DPP from December 2016 to December 2017. The program incorporates interactive mobile computing, remote monitoring, an evidence-based curriculum, behavior tracking tools, health coaching, and online peer support to prevent or delay the onset of type 2 diabetes. The analysis included data that were collected at baseline and after 4 months of the Transform DPP. RESULTS: The sample (N=273) comprised people with prediabetes who completed 4 months of the Transform program. Participants included 70.3% women, with a mean age of 54.0 (SD 11.2) years. On average, participants decreased their weight by 13.3 lbs (6.5%) and their BMI by 1.9 kg/m2. On average, participants increased their exercise frequency by 1.7 days per week, and absenteeism was reduced by almost half a day per month. CONCLUSIONS: These results suggest that the digital therapeutic DPP (Transform) is effective at preventing type 2 diabetes through a significant reduction in body weight and an increase of physical activity. A prospective, controlled clinical study is warranted to validate these findings.

Diabetes and the occurrence of infection in primary care: a matched cohort study.

BACKGROUND: People with diabetes may be at higher risk for acquiring infections through both glucose-dependent and biologic pathways independent of glycemic control. Our aim was to estimate the association between diabetes and infections occurring in primary care. METHODS: Using the Newfoundland and Labrador Sentinel of the Canadian Primary Care Sentinel Surveillance Network, patients with diabetes ≥18 years between 1 January 2008 and 31 March 2013 were included with at least 1-year of follow-up. We randomly matched each patient with diabetes on the date of study entry with up to 8 controls without diabetes. Primary outcome was the occurrence of ≥1 primary care physician visits for any infectious disease. Secondary outcomes included primary visits for head & neck, respiratory, gastrointestinal, genitourinary, skin and soft tissue, musculoskeletal, and viral infections. Using multivariable conditional logistic regression analysis, we measured the independent association between diabetes and the occurrence of infections. RESULTS: We identified 1779 patients with diabetes who were matched to 11,066 patients without diabetes. Patients with diabetes were older, had a higher prevalence of comorbidities, and were more often referred to specialists. After adjusting for potential confounders, patients with diabetes had an increased risk of any infection compared to patients without diabetes (adjusted odds ratio = 1.21, 95% confidence interval 1.07-1.37). Skin and soft tissue infections had the strongest association, followed by genitourinary, gastrointestinal, and respiratory infections. Diabetes was not associated with head and neck, musculoskeletal, or viral infections. CONCLUSION: Patients with diabetes appear to have an increased risk of certain infections compared to patients without diabetes.

The association between diabetes mellitus and incident infections: a systematic review and meta-analysis of observational studies.

OBJECTIVE: To quantify the association between diabetes and the risk of incident infections by conducting a systematic review and meta-analysis. RESEARCH DESIGN AND METHODS: Two reviewers independently screened articles identified from PubMed, EMBASE, Cochrane Library, IPA, and Web of Science databases. Cohort studies (CS) or case-control studies (CCS) evaluating the incidence of infections in adults with diabetes were included. Infections were classified as: skin and soft tissue, respiratory, blood, genitourinary, head and neck, gastrointestinal, bone, viral, and non-specified infections. Study quality was assessed using the Newcastle-Ottawa Quality Assessment Scale. Summary crude and adjusted OR with 95% CIs were calculated using random effects models, stratified by study design. Heterogeneity was measured using the I2statistic and explored using subgroup analyses. RESULTS: A total of 345 (243 CS and 102 CCS) studies were included. Combining adjusted results from all CS, diabetes was associated with an increased incidence of skin (OR 1.94, 95% CI 1.78 to 2.12), respiratory (OR 1.35, 95% CI 1.28 to 1.43), blood (OR 1.72, 95% CI 1.48 to 2.00), genitourinary (OR 1.61, 95% CI 1.42 to 1.82), head and neck (OR 1.17, 95% CI 1.13 to 1.22), gastrointestinal (OR 1.48, 95% CI 1.40 to 1.57), viral (OR 1.29, 95% CI 1.13 to 1.46), and non-specified (OR 1.84, 95% CI 1.66 to 2.04) infections. A stronger association was observed among CCS: skin (OR 2.64, 95% CI 2.20 to 3.17), respiratory (OR 1.62, 95% CI 1.37 to 1.92), blood (OR 2.40, 95% CI 1.68 to 3.42), genitourinary (OR 2.59, 95% CI 1.60 to 4.17), gastrointestinal (OR 3.61, 95% CI 2.94 to 4.43), and non-specified (OR 3.53, 95% CI 2.62 to 4.75). CONCLUSION: Diabetes is associated with an increased risk of multiple types of infections. A high degree of heterogeneity was observed; however, subgroup analysis decreased the amount of heterogeneity within most groups. Results were generally consistent across types of infections.

Effectiveness of a pharmacist-driven intervention in COPD (EPIC): study protocol for a randomized controlled trial.

BACKGROUND: Patients with chronic obstructive pulmonary disease (COPD) are often nonadherent with medications and have poor inhaler technique. Community pharmacists can help to improve health-related quality of life and overall outcomes in patients with COPD. We aim to measure the effectiveness of a systematic, pharmacist-driven intervention on patients with diagnosed COPD. METHODS/DESIGN: This pragmatic, parallel-group, cluster randomized controlled trial is designed to determine the effectiveness of a multifactorial, pharmacist-led intervention on medication adherence, inhaler technique, health-related quality of life, health care resource utilization including COPD exacerbations, and use of medications. Participating pharmacies in Newfoundland and Labrador (NL), Canada will be randomly assigned to either the intervention or the control group. The intervention group will deliver an enhanced form of care that emphasizes COPD management. The control group will provide usual care and a COPD education pamphlet. Included patients will be aged 40 years or older, have a physician-confirmed diagnosis of COPD, and be able to answer questionnaires in English. The primary outcomes are the between-group difference in the change from baseline to 6 months in medication adherence using the Medication Possession Ratio (MPR) and the Morisky Medication Adherence Scale (MMAS-8). The secondary outcomes are also measured from baseline to 6 months, and include the proportion of patients with a clinically significant change in adherence, the proportion of patients defined as having "good adherence," the mean MPR between groups, quality of life as measured by the St. George's Respiratory Questionnaire, medication inhalation technique using a pharmacist-scored checklist, health care resource utilization and antibiotic and orally administered corticosteroid use for COPD exacerbations. Differences between groups will be analyzed at the individual patient level while controlling for clustering effect. DISCUSSION: A pharmacist-led COPD intervention has the potential to improve patient medication adherence, thus increasing quality of life, possibly decreasing pulmonary exacerbations and reducing utilization of acute health care resources. Methods and results taken from this study could be used to enhance the delivery of COPD care by community pharmacists in a real-world setting. This would serve to enhance COPD population health and quality of life. TRIAL REGISTRATION: International Standard Randomized Controlled Trial Number (ISRCTN) ISRCTN78138190 , registered on 3 February 2016.

The Effect of Smartphone Interventions on Patients With Chronic Obstructive Pulmonary Disease Exacerbations: A Systematic Review and Meta-Analysis.

BACKGROUND: The prevalence and mortality rates of chronic obstructive pulmonary disease (COPD) are increasing worldwide. Therefore, COPD remains a major public health problem. There is a growing interest in the use of smartphone technology for health promotion and disease management interventions. However, the effectiveness of smartphones in reducing the number of patients having a COPD exacerbation is poorly understood. OBJECTIVE: To summarize and quantify the association between smartphone interventions and COPD exacerbations through a comprehensive systematic review and meta-analysis. METHODS: A comprehensive search strategy was conducted across relevant databases (PubMed, Embase, Cochrane, CINHA, PsycINFO, and the Cochrane Library Medline) from inception to October 2015. We included studies that assessed the use of smartphone interventions in the reduction of COPD exacerbations compared with usual care. Full-text studies were excluded if the investigators did not use a smartphone device or did not report on COPD exacerbations. Observational studies, abstracts, and reviews were also excluded. Two reviewers extracted the data and conducted a risk of bias assessment using the US Preventive Services Task Force quality rating criteria. A random effects model was used to meta-analyze the results from included studies. Pooled odds ratios were used to measure the effectiveness of smartphone interventions on COPD exacerbations. Heterogeneity was measured using the I(2)statistic. RESULTS: Of the 245 unique citations screened, 6 studies were included in the qualitative synthesis. Studies were relatively small with less than 100 participants in each study (range 30 to 99) and follow-up ranged from 4-9 months. The mean age was 70.5 years (SD 5.6) and 74% (281/380) were male. The studies varied in terms of country, type of smartphone intervention, frequency of data collection from the participants, and the feedback strategy. Three studies were included in the meta-analysis. The overall assessment of potential bias of the studies that were included in the meta-analysis was "Good" for one study and "Fair" for 2 studies. The pooled random effects odds ratio of patients having an exacerbation was 0.20 in patients using a smartphone intervention (95% CI 0.07-0.62), a reduction of 80% for smartphone interventions compared with usual care. However, there was moderate heterogeneity across the included studies (I(2)=59%). CONCLUSION: Although current literature on the role of smartphones in reducing COPD exacerbations is limited, findings from our review suggest that smartphones are useful in reducing the number of patients having a COPD exacerbation. Nevertheless, using smartphones require synergistic strategies to achieve the desired outcome. These results should be interpreted with caution due to the heterogeneity among the studies. Researchers should focus on conducting rigorous studies with adequately powered sample sizes to determine the validity and clinical utility of smartphone interventions in the management of COPD.